© 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. 148517
    Prev
    Next
    INDEX
    Explanations

    dates and events

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

    goals and conditional requirements

    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
    る
    0.41
    accessor
    0.40
    偏
    0.40
    ţi
    0.39
    invoice
    0.39
    ると
    0.39
     renseign
    0.38
    accessory
    0.38
    如
    0.38
    outstanding
    0.38
    POSITIVE LOGITS
     Januari
    0.59
     Plague
    0.57
     Hay
    0.52
     होनी
    0.52
     Debe
    0.52
     Must
    0.51
     Duluth
    0.51
     Trebuie
    0.51
     February
    0.50
     Mardi
    0.50
    Activations Density 0.000%

    No Known Activations