© 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. 189739
    Prev
    Next
    INDEX
    Explanations

    money, covers, supplying, includes, autoclave

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

    ends of phrases and sentences

    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
    زمت
    0.31
    運用
    0.30
    ಹ
    0.30
    북도
    0.29
    מ
    0.29
    ברי
    0.28
    아야
    0.28
    ULATION
    0.27
     remarkable
    0.27
     रहना
    0.27
    POSITIVE LOGITS
    ,_
    0.36
    ,//
    0.35
    iid
    0.34
    _(
    0.34
    nonce
    0.34
     thải
    0.33
    exch
    0.33
    WCHAR
    0.33
    adiya
    0.33
    gf
    0.32
    Activations Density 0.206%

    No Known Activations