© 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. 36701
    Prev
    Next
    INDEX
    Explanations

    available amenities

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

    technical and health topics

    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
    kelig
    0.56
    靶
    0.44
     alatt
    0.43
     bijz
    0.43
     মন্দির
    0.43
     conductas
    0.42
     voet
    0.42
    דרך
    0.42
    荿
    0.42
    ளமான
    0.41
    POSITIVE LOGITS
     ChatGPT
    0.47
     TV
    0.43
     done
    0.42
     El
    0.40
     Elect
    0.39
     Cin
    0.39
     KN
    0.39
     HR
    0.38
     Delight
    0.38
     Compose
    0.38
    Activations Density 0.001%

    No Known Activations