© 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. 142291
    Prev
    Next
    INDEX
    Explanations

    data processing and legal matters

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

    Maiar

    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
    train
    0.46
     الاثنين
    0.44
    ignore
    0.42
    plasma
    0.42
    兩
    0.42
    nergy
    0.40
    loading
    0.40
    ᱑
    0.39
    nights
    0.39
    的所有
    0.39
    POSITIVE LOGITS
     DIGITAL
    0.58
     OKC
    0.55
     bespoke
    0.53
     digital
    0.52
     esim
    0.52
     Samson
    0.51
     photo
    0.50
     Burgundy
    0.49
     EDC
    0.49
     KO
    0.48
    Activations Density 0.000%

    No Known Activations