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. 4056
    Prev
    Next
    INDEX
    Explanations

    endings and descriptions

    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
    க்கு
    0.98
    ’
    0.94
     που
    0.93
     என்று
    0.93
     えっと
    0.88
     районе
    0.88
     असल्याचे
    0.88
     setempat
    0.88
    🍂
    0.86
    '
    0.85
    POSITIVE LOGITS
    AN
    1.03
    зывают
    0.95
     handset
    0.95
    AT
    0.94
    IoT
    0.90
     kyll
    0.89
    AR
    0.89
     detonation
    0.88
     powertrain
    0.85
    ak
    0.84
    Activations Density 0.149%

    No Known Activations