© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21235
    Prev
    Next
    INDEX
    Explanations

    indicated in brackets

    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
    -
    0.52
     or
    0.49
    he
    0.48
    is
    0.48
    .
    0.46
    ž
    0.46
    é
    0.45
    era
    0.45
     insp
    0.45
    service
    0.45
    POSITIVE LOGITS
    hatiti
    0.46
    ዐይን
    0.45
    <unused985>
    0.44
     detd
    0.44
     kehnd
    0.43
     pathophys
    0.43
    Concini
    0.43
     vectơ
    0.42
    ளிலும்
    0.42
     focussing
    0.42
    Activations Density 0.000%

    No Known Activations