© 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. 44280
    Prev
    Next
    INDEX
    Explanations

    rule of thirds

    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
    Can
    0.89
    ال
    0.81
    the
    0.79
    ská
    0.79
    能
    0.79
    ský
    0.78
    Woo
    0.77
    ୟ
    0.75
     dịp
    0.74
    Spring
    0.71
    POSITIVE LOGITS
    вт
    0.89
    gebaut
    0.85
     Regione
    0.85
     Herstellung
    0.80
     Statistik
    0.79
    gefühl
    0.77
    fragen
    0.77
     Statist
    0.77
     Flächen
    0.76
     來
    0.76
    Activations Density 0.000%

    No Known Activations