© 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. 120386
    Prev
    Next
    INDEX
    Explanations

    per cent

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

    perhaps optional

    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
     factorización
    0.57
    𐰺
    0.54
     possibilités
    0.52
    ধান
    0.49
    ꒰
    0.48
     !!,
    0.48
     సందర్భంగా
    0.47
    ینا
    0.47
    ):["
    0.46
    ྰ
    0.46
    POSITIVE LOGITS
    0.45
     looking
    0.45
     Are
    0.43
     are
    0.40
    GR
    0.40
     identifying
    0.40
     struggling
    0.40
    機関
    0.39
    acting
    0.39
     lok
    0.39
    Activations Density 0.001%

    No Known Activations