© 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. 270
    Prev
    Next
    INDEX
    Explanations

    categorized lists

    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
    Ahora
    0.75
    Seg
    0.70
    TIMESTAMP
    0.68
     petites
    0.67
    });
    0.66
    SU
    0.66
    Jessica
    0.66
    sufficiency
    0.65
    #!/
    0.64
    णात
    0.64
    POSITIVE LOGITS
    joon
    0.87
     radia
    0.84
     knit
    0.81
    كا
    0.80
    ísmo
    0.79
     determ
    0.78
    ğini
    0.77
     distaste
    0.77
    czki
    0.77
    ukaemia
    0.76
    Activations Density 0.001%

    No Known Activations