© 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. 117309
    Prev
    Next
    INDEX
    Explanations

    intermediate levels and stages

    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
    <0x80>
    -1.08
    bottomrule
    -1.02
     cuối
    -0.98
    Lastly
    -0.95
    ⎭
    -0.93
     endgame
    -0.92
     Lastly
    -0.92
    最后
    -0.91
    最後に
    -0.90
    สุด
    -0.89
    POSITIVE LOGITS
     middle
    2.88
     intermediate
    2.56
    middle
    2.36
     mid
    2.23
    intermediate
    2.19
     medium
    2.09
     Intermediate
    1.95
    Intermediate
    1.94
    Middle
    1.91
    MIDDLE
    1.86
    Activations Density 0.175%

    No Known Activations