© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43830
    Prev
    Next
    INDEX
    Explanations

    links, numbers, followed by specific input

    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
    els
    0.44
    '
    0.44
    方式
    0.42
    🥛
    0.41
    ```
    0.40
    elt
    0.40
    let
    0.40
    Volt
    0.39
    enough
    0.39
    nal
    0.39
    POSITIVE LOGITS
     institu
    0.49
     başlat
    0.49
     enteric
    0.47
     touristic
    0.46
     успех
    0.46
     popula
    0.46
     később
    0.45
    ➝
    0.45
     immunological
    0.44
     alcan
    0.44
    Activations Density 0.002%

    No Known Activations