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. 6565
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    V
    0.97
    т
    0.93
    И
    0.92
    If
    0.91
    T
    0.89
    The
    0.88
    With
    0.88
    En
    0.83
    F
    0.83
    Q
    0.82
    POSITIVE LOGITS
     hypersurfaces
    1.20
     Faun
    0.91
    幻想
    0.87
     eukaryotes
    0.86
     adamant
    0.86
     hypersurface
    0.86
    тары
    0.85
     Mosul
    0.84
     Ceg
    0.84
     Tjiwarl
    0.83
    Activations Density 0.000%

    No Known Activations