© 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. 130921
    Prev
    Next
    INDEX
    Explanations

    before shipment

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

    recreation and abstract concepts

    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
    ଘ
    0.56
    🟠
    0.46
    ≜
    0.46
    quando
    0.46
     когато
    0.45
     notably
    0.45
    🏦
    0.45
     Например
    0.45
     когда
    0.44
     keď
    0.44
    POSITIVE LOGITS
     cần
    0.52
    I
    0.47
     I
    0.46
     secund
    0.45
     falso
    0.44
     Lite
    0.42
     Kollegen
    0.42
     collega
    0.42
     Secondo
    0.42
     Forrest
    0.42
    Activations Density 0.001%

    No Known Activations