© 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-65K
    7. 4762
    Prev
    Next
    INDEX
    Explanations

    software installation commands

    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_65k_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
     dày
    0.39
    猎
    0.39
    QUENCY
    0.39
    蔗
    0.39
     ক্যাল
    0.39
    utto
    0.39
    RationalValue
    0.39
     हाथी
    0.38
    빚
    0.38
     کمپ
    0.38
    POSITIVE LOGITS
     Manitoba
    0.50
    Kansas
    0.48
    jboss
    0.47
     aggravated
    0.43
    Minneapolis
    0.43
    kafka
    0.42
    защи
    0.41
     SLAs
    0.41
     Winnipeg
    0.41
    urken
    0.41
    Activations Density 0.051%

    No Known Activations