© 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. 123166
    Prev
    Next
    INDEX
    Explanations

    proximity and combination

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

    personal connection and risk

    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
    ?!
    0.55
     এমনকি
    0.50
    私も
    0.50
     हल्ला
    0.49
     хто
    0.49
    橛
    0.48
     ähm
    0.47
     आग्रह
    0.47
     多く
    0.47
     সুতরাং
    0.47
    POSITIVE LOGITS
     enhances
    0.56
     computerized
    0.50
     stets
    0.50
     improves
    0.49
     phases
    0.48
    AS
    0.47
    (
    0.47
     stimulates
    0.47
     tetromino
    0.47
     stimulate
    0.46
    Activations Density 0.001%

    No Known Activations