© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32254
    Prev
    Next
    INDEX
    Explanations

    CrossFit, Oxaliplatin, Labile, Q:

    np_acts-logits-general · gemini-2.5-flash-lite

    information about ownership or possession, often indicated by the word "of".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on the token “History,” i.e. it is specifically detecting that exact word.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hanced
    -1.00
    ebly
    -0.98
    шна
    -0.93
    下一页
    -0.90
     constant
    -0.90
     uzyskać
    -0.90
    constant
    -0.89
    靼
    -0.89
    gged
    -0.87
    ))$.
    -0.86
    POSITIVE LOGITS
     this
    1.31
     concern
    0.92
    OUR
    0.91
    نس
    0.90
     product
    0.88
     our
    0.87
     Verfasser
    0.87
    inkt
    0.86
    うち
    0.86
    受
    0.86
    Activations Density 0.000%

    No Known Activations