© 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. 60299
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    election results

    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
     электронной
    0.50
    :&
    0.46
     arrows
    0.44
     хотела
    0.43
    :.
    0.43
     odometer
    0.43
    ittees
    0.42
     scoreboard
    0.42
     смогут
    0.42
     автором
    0.42
    POSITIVE LOGITS
    lı
    0.47
    ﺟ
    0.47
     Aqui
    0.45
    ｱ
    0.45
    jate
    0.44
    instagram
    0.44
    insta
    0.44
    js
    0.43
    groups
    0.43
    mountain
    0.42
    Activations Density 0.003%

    No Known Activations