© 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. 245844
    Prev
    Next
    INDEX
    Explanations

    selection and position

    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
    グ
    0.49
    ั
    0.46
    dri
    0.43
     αργ
    0.43
    δέ
    0.43
    δι
    0.43
    았
    0.42
    hadas
    0.42
    atura
    0.41
    eret
    0.40
    POSITIVE LOGITS
     wünschen
    0.53
    ℡
    0.49
    -(\
    0.49
     помогут
    0.48
     લાભ
    0.47
     Brings
    0.47
     junto
    0.47
     Wich
    0.47
     Enables
    0.46
     سہ
    0.46
    Activations Density 0.003%

    No Known Activations