© 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. 139275
    Prev
    Next
    INDEX
    Explanations

    entertaining

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

    structured lists and enumerations

    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
     focussed
    0.51
    weeney
    0.50
     ఏద
    0.50
    timevals
    0.49
    ຢູ່
    0.47
    ordano
    0.47
    řed
    0.46
    ἱ
    0.46
     ವೀರ
    0.46
     Право
    0.46
    POSITIVE LOGITS
    s
    0.66
    y
    0.53
     Buckley
    0.51
     Systems
    0.49
     Packard
    0.48
     Ling
    0.48
     Norm
    0.48
    e
    0.47
    o
    0.46
     Seat
    0.46
    Activations Density 0.000%

    No Known Activations