Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38314
    Prev
    Next
    INDEX
    Explanations

    throw new Error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.91
    ’
    1.65
     toch
    1.55
     Abgerufen
    1.46
     Während
    1.43
     cambiando
    1.42
     queria
    1.41
    €™
    1.39
     gestire
    1.36
     ਡ
    1.35
    POSITIVE LOGITS
    ۹
    1.46
    های
    1.31
    습니다
    1.24
    ımız
    1.23
    ları
    1.22
    AN
    1.20
    IR
    1.20
    RE
    1.18
    他
    1.17
    кость
    1.16
    Activations Density 0.002%

    No Known Activations