© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 120527
    Prev
    Next
    INDEX
    Explanations

    improve the, entire stack, wanted to

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

    tails, method, standards

    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
    COLUMN
    0.49
    商城
    0.44
     pouss
    0.42
    Command
    0.42
    r
    0.42
    command
    0.41
    されます
    0.40
    秒
    0.40
    SEARCH
    0.39
    TOTAL
    0.39
    POSITIVE LOGITS
     didn
    0.56
     doesn
    0.48
     wasn
    0.47
     applicable
    0.47
     inherently
    0.47
    ບໍ່
    0.46
     unfortunate
    0.45
     familiarity
    0.45
     portability
    0.44
     same
    0.44
    Activations Density 0.000%

    No Known Activations