© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 220356
    Prev
    Next
    INDEX
    Explanations

    literally boosts

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

    specifying criteria when

    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
    ম
    0.56
    ي
    0.51
    ل
    0.50
    ق
    0.50
     güzel
    0.49
    ある
    0.48
    ח
    0.48
    л
    0.47
    ح
    0.47
    ியை
    0.46
    POSITIVE LOGITS
     Writings
    0.48
     الحل
    0.46
     Unable
    0.45
    枭
    0.45
     उड़
    0.45
     फैली
    0.44
     Salts
    0.44
     Stateful
    0.43
     Penalty
    0.43
     Temporary
    0.43
    Activations Density 0.001%

    No Known Activations