© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1637
    Prev
    Next
    INDEX
    Explanations

    prompts as instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Organisation
    2.53
     historians
    2.35
    Organisation
    2.34
     organisers
    2.31
    佢
    2.27
    来说
    2.26
     organisation
    2.25
    年は
    2.23
     Brides
    2.20
    ungannya
    2.13
    POSITIVE LOGITS
     instinctively
    3.14
     באופן
    3.14
     immédiatement
    3.07
    rinsic
    2.99
    7
    2.88
    immediately
    2.83
     imediatamente
    2.82
     unilaterally
    2.79
    quetas
    2.78
     irres
    2.77
    Activations Density 3.846%

    No Known Activations