© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42992
    Prev
    Next
    INDEX
    Explanations

    session management, communication, states, themes

    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
    construct
    0.80
    वर्ड
    0.78
    兵
    0.77
    ждый
    0.75
    OC
    0.75
    al
    0.74
    ওয়ার্ড
    0.73
    </sub>
    0.73
    кость
    0.71
    эро
    0.71
    POSITIVE LOGITS
     avuto
    1.05
     données
    0.92
     avaient
    0.92
     avere
    0.91
     partito
    0.90
     soit
    0.86
     împ
    0.86
     poter
    0.86
     aveva
    0.84
     sia
    0.82
    Activations Density 0.000%

    No Known Activations