© 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. 184295
    Prev
    Next
    INDEX
    Explanations

    legal and specific terms

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

    Confirm, Talk, why, should, be

    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
     Biotechnology
    0.48
     витами
    0.48
     coordinates
    0.46
     Biochem
    0.45
     olvides
    0.44
     دوبارہ
    0.43
    笹
    0.43
     alumnos
    0.43
    都需要
    0.42
     manteniendo
    0.42
    POSITIVE LOGITS
    ಿಸಿದ್ದರು
    0.50
     pitted
    0.48
     splashed
    0.48
     unquestionably
    0.46
     insufficiently
    0.44
     recklessly
    0.44
     defensively
    0.42
     offent
    0.42
    <unused406>
    0.42
     abroad
    0.42
    Activations Density 0.000%

    No Known Activations