© 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. 148373
    Prev
    Next
    INDEX
    Explanations

    Absolutely

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

    predicting what comes next

    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
    ط
    0.53
    ă
    0.48
    inz
    0.47
    ore
    0.46
     էին
    0.46
    MM
    0.45
    ә
    0.45
    usu
    0.45
    oce
    0.45
    a
    0.45
    POSITIVE LOGITS
     Wicked
    0.52
    რივ
    0.49
     CQL
    0.48
    👒
    0.46
    함을
    0.45
     encounters
    0.44
    ͢
    0.43
    요일
    0.43
     isOn
    0.43
     packs
    0.42
    Activations Density 0.000%

    No Known Activations