© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 355
    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
    вых
    1.03
    ются
    0.80
    ৬০
    0.80
    вые
    0.80
    ра
    0.75
    вы
    0.75
    ת
    0.75
     второй
    0.75
     Φ
    0.73
     неприят
    0.72
    POSITIVE LOGITS
     sits
    0.86
    g
    0.84
    igham
    0.82
     avaient
    0.80
    care
    0.79
     accueille
    0.79
     formes
    0.79
    LG
    0.78
    िक्ट
    0.78
     住
    0.78
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.