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

    Neuronpedia

    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. 39157
    Prev
    Next
    INDEX
    Explanations

    retention policy / support vector machine

    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
    ਾ
    1.31
     geodes
    1.17
     correspondant
    1.10
     cantor
    1.07
     president
    1.05
     জীবা
    1.05
     खरीदना
    1.05
    метри
    1.04
     bain
    1.03
    uction
    1.02
    POSITIVE LOGITS
    જ
    1.68
     adhesions
    1.42
    м
    1.42
    ン
    1.41
    平时
    1.39
    ক
    1.38
    ಟರ್
    1.37
    ни
    1.36
    па
    1.36
    ص
    1.36
    Activations Density 0.004%

    No Known Activations