© 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. 61805
    Prev
    Next
    INDEX
    Explanations

    internal model

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

    capabilities and conditions

    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
    ירת
    0.46
    –
    0.44
    ({
    0.43
    swan
    0.41
     jwt
    0.40
     Shuk
    0.40
     সে
    0.39
    ー
    0.39
    সহ
    0.38
    ர்
    0.38
    POSITIVE LOGITS
    ListPage
    0.49
    bindings
    0.45
    𝗲
    0.45
     рэгістрацыі
    0.44
     pouvaient
    0.44
    grids
    0.44
     ため
    0.43
     칸
    0.42
     نے
    0.41
     fossero
    0.41
    Activations Density 0.000%

    No Known Activations