© 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. 30376
    Prev
    Next
    INDEX
    Explanations

    Meta, LLAMA2

    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
     Geiger
    0.49
    </h2>
    0.46
     Уже
    0.44
     ");
    0.44
     особи
    0.44
    LLING
    0.43
     \
    0.42
    ED
    0.42
     домаћинствима
    0.42
    LEN
    0.42
    POSITIVE LOGITS
    াঙ্গীর
    0.49
    encils
    0.46
    ంచెం
    0.46
     অর্চনা
    0.45
    adoop
    0.44
    Crunch
    0.44
     রাজেশ
    0.44
     vistazo
    0.43
     remastered
    0.42
    ंग्रेस
    0.42
    Activations Density 0.001%

    No Known Activations