© 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. 37501
    Prev
    Next
    INDEX
    Explanations

    be followed by predicate

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

    be preparing something

    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
     overestimated
    0.46
     a
    0.44
     as
    0.44
     have
    0.43
     overgrown
    0.43
     create
    0.42
     underestimated
    0.42
     induce
    0.42
     begin
    0.41
    ’
    0.41
    POSITIVE LOGITS
    ੯
    0.49
    <unused26>
    0.44
     فرانس
    0.43
    ០០
    0.42
     која
    0.41
    گي
    0.41
    ㄢ
    0.40
    лору
    0.40
     आचार्य
    0.40
    لاً
    0.39
    Activations Density 0.062%

    No Known Activations