© 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. 1334
    Prev
    Next
    INDEX
    Explanations

    comfort and comfort related states

    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
    ان
    2.47
    न
    2.44
    ن
    2.44
    ה
    2.02
    ل
    1.84
    ン
    1.84
    ל
    1.82
     publiques
    1.71
    ક
    1.69
    ন
    1.65
    POSITIVE LOGITS
    (\
    2.09
    taining
    1.91
    inducing
    1.90
    inkl
    1.88
    ̉a
    1.87
    Counc
    1.84
    aneers
    1.81
    asp
    1.80
    সে
    1.79
    ade
    1.78
    Activations Density 0.064%

    No Known Activations