© 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. 20730
    Prev
    Next
    INDEX
    Explanations

    future actions or states

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

    screwdriver set

    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
    IS
    0.55
    km
    0.54
    ION
    0.53
    IP
    0.52
    5
    0.49
    7
    0.48
    CONFIG
    0.47
    US
    0.46
    4
    0.46
    IM
    0.45
    POSITIVE LOGITS
     seraient
    0.55
     auront
    0.53
     nebude
    0.52
     appelée
    0.50
     réserv
    0.49
     haies
    0.49
     terem
    0.48
     naturelles
    0.48
     absoluto
    0.48
     avere
    0.48
    Activations Density 0.000%

    No Known Activations