© 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. 66821
    Prev
    Next
    INDEX
    Explanations

    following lists or specific entities

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

    qualifications or consequences

    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
     enormously
    0.49
    m
    0.47
     d
    0.46
    sa
    0.46
    DC
    0.44
     extraordinarily
    0.44
    dc
    0.43
    čaj
    0.43
    이야
    0.42
    mw
    0.42
    POSITIVE LOGITS
    ्याज
    0.48
     табли
    0.48
    检索
    0.48
    绁
    0.48
    ార్లు
    0.47
    訒
    0.47
    вят
    0.46
    eredReader
    0.46
     jobSearch
    0.46
    畋
    0.45
    Activations Density 0.001%

    No Known Activations