© 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. 62968
    Prev
    Next
    INDEX
    Explanations

    Release Body

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

    less sensitive, cold, models, simple

    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
    יי
    0.50
    ar
    0.50
    л
    0.48
    il
    0.46
    IfExists
    0.46
     రాజకీయ
    0.45
    restaurants
    0.45
    Smartphone
    0.45
    亣
    0.45
    ificador
    0.45
    POSITIVE LOGITS
     —
    0.42
     }}{
    0.42
     Sacchar
    0.40
     EL
    0.40
     அறிமுக
    0.39
    ゴール
    0.38
     ANA
    0.38
     Euph
    0.38
     Release
    0.37
     обнов
    0.37
    Activations Density 0.001%

    No Known Activations