© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218929
    Prev
    Next
    INDEX
    Explanations

    welcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    API endpoints, JSON, CSV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    气体
    0.49
    ۇ
    0.49
     bald
    0.47
    ഗി
    0.46
    ල්
    0.46
    количество
    0.45
     चिंग
    0.45
     schoolchildren
    0.44
     zaidi
    0.44
    izh
    0.44
    POSITIVE LOGITS
     ましょう
    0.55
     "</
    0.49
    ↴
    0.46
     apari
    0.43
    </html>
    0.42
     '.</
    0.42
    敏
    0.42
    otip
    0.41
    > </
    0.40
    :</
    0.40
    Activations Density 0.000%

    No Known Activations