© 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. 206785
    Prev
    Next
    INDEX
    Explanations

    generation that

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

    names, locations, and "room"

    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
     PRICES
    0.48
    SpacerItem
    0.45
     交
    0.45
     整
    0.44
     ২০০
    0.43
    管理的
    0.43
    IndexArray
    0.42
     />);
    0.42
    নিং
    0.42
    Celltype
    0.42
    POSITIVE LOGITS
    ک
    0.55
     our
    0.55
    up
    0.54
    vg
    0.53
    当社
    0.53
    in
    0.49
    kamp
    0.49
    vor
    0.48
    von
    0.48
    ing
    0.48
    Activations Density 0.002%

    No Known Activations