© 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. 117363
    Prev
    Next
    INDEX
    Explanations

    code license terms

    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
     souverain
    -0.88
    らか
    -0.85
    亵
    -0.83
     recenz
    -0.83
     charlotte
    -0.82
     restante
    -0.82
    もう
    -0.81
    <0x00>
    -0.81
    quite
    -0.81
     filozof
    -0.81
    POSITIVE LOGITS
     provides
    0.74
     Despite
    0.73
    Thank
    0.72
     няколко
    0.72
    mmers
    0.71
     or
    0.70
     falling
    0.70
     kotor
    0.69
     baka
    0.69
    嫦
    0.68
    Activations Density 0.185%

    No Known Activations