© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219364
    Prev
    Next
    INDEX
    Explanations

    neglected considerations

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

    legal/formal clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    铡
    0.60
    睢
    0.52
    امہ
    0.50
    嚗
    0.50
    ফে
    0.49
    Мі
    0.48
    FBI
    0.48
    Anaconda
    0.48
    André
    0.47
    璈
    0.47
    POSITIVE LOGITS
    ate
    0.52
     crippled
    0.52
    irá
    0.51
    ity
    0.50
     sanctuary
    0.50
    ated
    0.50
     земли
    0.50
     тела
    0.49
    usions
    0.49
     modality
    0.48
    Activations Density 0.000%

    No Known Activations