© 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. 157314
    Prev
    Next
    INDEX
    Explanations

    renting services and advice

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

    questions and clarifications

    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
     poles
    0.54
    志森
    0.50
    د
    0.49
    GEBURTSDATUM
    0.48
     AirPods
    0.47
    ᇁ
    0.47
     paramètres
    0.46
    𒉡
    0.46
    سمى
    0.46
     pierres
    0.46
    POSITIVE LOGITS
     Maha
    0.49
    mah
    0.49
     ইরা
    0.43
     Mah
    0.43
    ma
    0.43
     Hmm
    0.42
     Http
    0.42
     Poon
    0.41
     Baghdad
    0.40
     Dynasty
    0.40
    Activations Density 0.002%

    No Known Activations