© 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. 143411
    Prev
    Next
    INDEX
    Explanations

    may involve phrases

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

    Adopt, readiness, prioritized functionality

    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
     مثل
    0.47
    \;
    0.44
    掝
    0.44
    Wikipedia
    0.43
    Elems
    0.43
    人类
    0.42
    بخ
    0.41
     Boston
    0.41
    鈔
    0.41
    ovod
    0.40
    POSITIVE LOGITS
    s
    0.57
     behavi
    0.48
    bungen
    0.48
     behavioural
    0.46
     sourcing
    0.46
     Bezir
    0.46
    y
    0.46
    님
    0.45
    ;%%
    0.45
     kolor
    0.45
    Activations Density 0.001%

    No Known Activations