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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32567
    Prev
    Next
    INDEX
    Explanations

    geographical regions and names

    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
    нига
    0.48
     prices
    0.47
     monoclonal
    0.45
     trei
    0.45
    շ
    0.43
     obicei
    0.43
     prizes
    0.42
    ᖕ
    0.41
    环境下
    0.40
     bine
    0.40
    POSITIVE LOGITS
    feat
    0.45
    tes
    0.44
    Defined
    0.44
    as
    0.44
    prj
    0.43
    stehen
    0.43
    ide
    0.42
    ello
    0.42
    ifiziert
    0.40
    tan
    0.40
    Activations Density 0.000%

    No Known Activations