© 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. 24-GEMMASCOPE-2-RES-262K
    7. 8919
    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_24_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
     kicked
    0.65
    —
    0.65
     benefits
    0.64
    bled
    0.63
    বিষয়
    0.63
     fleeing
    0.61
    )—
    0.61
     constructed
    0.61
     chased
    0.60
    खाव
    0.60
    POSITIVE LOGITS
    м
    1.14
     VPS
    0.87
     Logitech
    0.82
     XRP
    0.82
    প্যাথ
    0.81
     liquide
    0.80
     용
    0.80
    い
    0.80
    и
    0.79
     NSLog
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.