© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34846
    Prev
    Next
    INDEX
    Explanations

    proclaimed, attributed, referral

    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
    s
    1.64
    v
    1.50
    lamp
    1.39
    n
    1.34
    inj
    1.29
    THING
    1.27
     Ora
    1.27
    Ο
    1.27
    cry
    1.26
     XXIII
    1.25
    POSITIVE LOGITS
    й
    1.45
    𝘪
    1.40
    𝘢
    1.39
    τερα
    1.37
    йга
    1.33
    на
    1.29
    ১৬
    1.28
    ք
    1.27
    一下
    1.26
    𝘰
    1.26
    Activations Density 0.001%

    No Known Activations