© 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. 92490
    Prev
    Next
    INDEX
    Explanations

    legal documentation keywords

    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
     even
    -0.99
    Even
    -0.89
     their
    -0.84
    gambar
    -0.83
    EPC
    -0.79
     could
    -0.79
     هو
    -0.79
     will
    -0.79
    kirche
    -0.77
     is
    -0.77
    POSITIVE LOGITS
    corro
    0.89
    STRUCTIONS
    0.84
    あー
    0.84
     guapos
    0.82
    rout
    0.79
    tabli
    0.79
    vibe
    0.79
    щата
    0.78
    avoid
    0.78
    缰
    0.77
    Activations Density 0.000%

    No Known Activations