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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 19728
    Prev
    Next
    INDEX
    Explanations

    set up or define

    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
    ⓡ,
    0.49
    ovjek
    0.44
    喆
    0.43
     pedro
    0.43
     teško
    0.42
     labyr
    0.42
     batsmen
    0.42
    itetty
    0.41
     hypnot
    0.41
     постепен
    0.41
    POSITIVE LOGITS
     CMC
    0.40
     CQ
    0.40
     geographic
    0.39
    <0x80>
    0.39
     recalls
    0.39
     نی
    0.39
     analytic
    0.39
     CLA
    0.38
     Deadline
    0.38
    Swap
    0.38
    Activations Density 0.010%

    No Known Activations