© 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. 14538
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    control, crew, confrontation, trip

    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
    ﱠ
    0.45
    όν
    0.42
    dbl
    0.42
    db
    0.41
    ává
    0.41
    ώρα
    0.40
    ulf
    0.39
    ⸝
    0.38
    dbi
    0.38
    secure
    0.38
    POSITIVE LOGITS
     Mannschaft
    0.43
     quelconque
    0.43
     katth
    0.42
     représentant
    0.42
     Mexique
    0.42
    ...";
    0.42
    ாண
    0.41
     théâtre
    0.41
     cathodes
    0.41
     quelcon
    0.40
    Activations Density 0.000%

    No Known Activations