© 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. 221518
    Prev
    Next
    INDEX
    Explanations

    from toroom thattries toholds theevening fromwere a

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

    android xml namespaces

    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
     mellett
    0.43
     scare
    0.42
    hardening
    0.41
    پ
    0.40
    在
    0.40
    ո
    0.40
     которого
    0.40
     ਦਾ
    0.39
    점
    0.39
     desarrollado
    0.38
    POSITIVE LOGITS
    humidité
    0.46
     circulación
    0.43
     kurzen
    0.43
    潺
    0.42
     寸
    0.41
     celebratory
    0.39
     flushed
    0.38
    Mp
    0.38
     Provo
    0.38
    ম্বা
    0.38
    Activations Density 0.000%

    No Known Activations