© 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. 41868
    Prev
    Next
    INDEX
    Explanations

    routine actions, advice, or hypothetical situations

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

    defining a state

    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
    3
    0.51
    Contribution
    0.49
    ;
    0.49
     Modes
    0.48
     Contribution
    0.48
     contribution
    0.47
     remote
    0.47
     modes
    0.47
     medications
    0.47
     Anch
    0.47
    POSITIVE LOGITS
     exécut
    0.50
     летом
    0.50
     έ
    0.49
     અથ
    0.49
     elección
    0.49
     قالت
    0.48
     feu
    0.47
     неделю
    0.47
     dijeron
    0.47
     tenía
    0.46
    Activations Density 0.000%

    No Known Activations