© 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. 34-GEMMASCOPE-RES-131K
    7. 106677
    Prev
    Next
    INDEX
    Explanations

    establish necessary conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     niektórych
    -1.01
     muitos
    -0.93
     многих
    -0.90
    ᄇ
    -0.89
    ῖν
    -0.85
     sedangkan
    -0.84
     skoro
    -0.84
     wielu
    -0.83
    itaji
    -0.83
     banyak
    -0.82
    POSITIVE LOGITS
     whatever
    2.63
     such
    2.59
     reasonable
    2.34
    whatever
    2.19
     any
    2.08
    Whatever
    1.98
     appropriate
    1.85
     suitable
    1.82
    reasonable
    1.77
    Reasonable
    1.77
    Activations Density 0.029%

    No Known Activations