© 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. 90518
    Prev
    Next
    INDEX
    Explanations

    holds up, reviews, bride

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

    compiler errors, Dijkstra, subsidy, captions, speed, scale, spelling, metaphor

    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
     Arkansas
    0.49
    mpl
    0.49
    ৷
    0.47
    ˇ
    0.47
     Duan
    0.46
    compos
    0.45
     চলচ্চিত্রের
    0.45
     Ad
    0.45
    F
    0.45
    xmax
    0.44
    POSITIVE LOGITS
     mist
    0.48
    क्यों
    0.44
     puk
    0.42
     disapp
    0.42
     illeg
    0.41
     uitvoering
    0.40
    Mist
    0.40
     Mist
    0.39
     disappointing
    0.39
     assassin
    0.39
    Activations Density 0.000%

    No Known Activations