© 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-65K
    7. 46516
    Prev
    Next
    INDEX
    Explanations

    code structure markers

    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
    s
    0.48
    }
    0.46
     (
    0.44
    //
    0.43
     */
    0.43
    剰
    0.43
    _{
    0.42
     }^{
    0.42
    अपनी
    0.42
     {
    0.41
    POSITIVE LOGITS
    ⚊
    0.45
    ‏:‏
    0.44
    ূর
    0.44
     każ
    0.43
    ৌজ
    0.42
     nécessite
    0.42
     সুবিধ
    0.41
     ayudarte
    0.41
     latérales
    0.41
     facilité
    0.41
    Activations Density 0.002%

    No Known Activations