© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35901
    Prev
    Next
    INDEX
    Explanations

    "tract" or "permissions"

    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
     moguće
    0.94
    ك
    0.93
    ида
    0.91
    ным
    0.89
    ્રોલ
    0.89
    ные
    0.87
     인한
    0.85
    <0x92>
    0.84
    près
    0.84
    ный
    0.83
    POSITIVE LOGITS
     Pam
    0.79
    cially
    0.79
     clutching
    0.78
    ˦
    0.77
    را
    0.76
    हिता
    0.76
     thisComponent
    0.76
    在了
    0.75
     commemorating
    0.75
    macher
    0.75
    Activations Density 0.000%

    No Known Activations