© 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. 55241
    Prev
    Next
    INDEX
    Explanations

    wants, wish, behind, salts, printed

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

    Privileged Bases, Notes, Episode V

    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
     Сі
    0.46
    ist
    0.45
     Mhm
    0.44
    Existe
    0.44
     Кі
    0.44
    çı
    0.43
     অনেকটাই
    0.43
    ،
    0.43
    arakat
    0.43
    ize
    0.42
    POSITIVE LOGITS
     testimonials
    0.50
     colore
    0.49
     incons
    0.49
     misdemean
    0.49
     lettera
    0.48
    譲
    0.48
     conto
    0.47
     contrats
    0.47
     illusions
    0.47
     argomento
    0.47
    Activations Density 0.000%

    No Known Activations