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. 3992
    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
     Phyt
    0.86
    agregar
    0.86
     cria
    0.82
    esercizio
    0.81
    "};
    0.79
    <unused2188>
    0.79
    orean
    0.79
     hypoallergenic
    0.79
     reina
    0.77
    elih
    0.77
    POSITIVE LOGITS
    েই
    0.80
    ैनल
    0.78
     pener
    0.76
    те
    0.75
    ル
    0.74
    পাকিস্ত
    0.72
    jih
    0.72
     perny
    0.72
    يًا
    0.71
     Iceland
    0.70
    Activations Density 0.000%

    No Known Activations