© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67434
    Prev
    Next
    INDEX
    Explanations

    outcomes of

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

    This neuron activates on words that express evaluation or importance—terms like “benefits,” “impact,” “value,” “consequences,” and “significance.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     who
    -1.63
    isième
    -1.48
    You
    -1.46
    </sub>
    -1.43
     was
    -1.42
    relenting
    -1.39
    ámicas
    -1.38
    ’)
    -1.37
    ();)
    -1.35
     был
    -1.33
    POSITIVE LOGITS
    1
    1.77
    5
    1.72
    3
    1.69
    8
    1.59
    6
    1.59
    2
    1.55
    4
    1.45
    0
    1.36
    がん
    1.35
     of
    1.33
    Activations Density 0.112%

    No Known Activations