© 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. 534
    Prev
    Next
    INDEX
    Explanations

    is something

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

    adjectives describing quality

    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
    VIOUS
    0.19
     这是
    0.18
    BrNO
    0.18
     божо
    0.17
     同
    0.17
     删除
    0.17
     沖縄
    0.17
     메소
    0.17
     Від
    0.17
     この
    0.17
    POSITIVE LOGITS
     incredibly
    0.32
     extremely
    0.30
     estremamente
    0.28
     exceedingly
    0.26
     highly
    0.26
     an
    0.26
     a
    0.25
     immensely
    0.25
     extremadamente
    0.25
     eminently
    0.25
    Activations Density 1.256%

    No Known Activations