© 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. 37892
    Prev
    Next
    INDEX
    Explanations

    should not be

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

    verbs followed by descriptions or actions

    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
    타
    0.48
     perpetrated
    0.47
     zlo
    0.47
     dissonance
    0.47
     delito
    0.46
     ダ
    0.46
     Datensch
    0.46
     punishable
    0.45
    Fecha
    0.43
     podataka
    0.43
    POSITIVE LOGITS
    μέ
    0.44
    দীর্ঘ
    0.43
    ưởng
    0.42
     Exeter
    0.42
     hài
    0.42
     într
    0.42
     activeButton
    0.42
    ເຮ
    0.41
    ﯿ
    0.41
     Voyage
    0.41
    Activations Density 0.000%

    No Known Activations