© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76816
    Prev
    Next
    INDEX
    Explanations

    history buffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ović
    0.46
     Не
    0.46
    Wit
    0.46
    ó
    0.46
     zd
    0.45
     specifica
    0.44
     záp
    0.43
     wit
    0.42
     สูตร
    0.42
     レ
    0.42
    POSITIVE LOGITS
    ة
    0.47
    race
    0.45
     detainees
    0.44
    r
    0.44
    ressive
    0.43
    दृ
    0.42
     زمانہ
    0.42
    病人
    0.42
     Aktion
    0.41
     murderous
    0.41
    Activations Density 0.002%

    No Known Activations