© 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. 9755
    Prev
    Next
    INDEX
    Explanations

    Pretty Stationery, Walk Away, Marketing, play areas

    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
    Incrementor
    0.96
    м
    0.94
     важ
    0.93
    ст
    0.91
    ляция
    0.91
     LUCKY
    0.89
    ógy
    0.88
     것도
    0.86
    л
    0.86
    дон
    0.85
    POSITIVE LOGITS
    s
    1.18
    ों
    1.13
    ere
    0.98
    ations
    0.89
     bandwagon
    0.89
     Steinmann
    0.87
    وان
    0.86
    ق
    0.86
     setzt
    0.86
     récemment
    0.84
    Activations Density 0.000%

    No Known Activations