© 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. 1196
    Prev
    Next
    INDEX
    Explanations

    ended up

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

    end up

    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
    ل
    0.43
    е
    0.42
     եւ
    0.41
    και
    0.40
    ната
    0.40
     zeker
    0.40
    лены
    0.39
     dhe
    0.39
    начала
    0.39
    ене
    0.39
    POSITIVE LOGITS
    tt
    0.41
    u
    0.41
    tta
    0.40
     needing
    0.40
    ta
    0.38
    in
    0.37
    變成
    0.36
     incidentally
    0.36
     Servant
    0.36
    os
    0.35
    Activations Density 0.068%

    No Known Activations