© 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. 16170
    Prev
    Next
    INDEX
    Explanations

    merchant account

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

    perhaps offer

    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
     entrando
    0.46
     অন্
    0.46
     berbentuk
    0.44
    醬
    0.44
    ళ్లు
    0.43
    ▦
    0.43
    荸
    0.43
    anaf
    0.42
    рка
    0.41
    Therates
    0.41
    POSITIVE LOGITS
     Exhibit
    0.43
    charg
    0.43
     And
    0.40
     ~
    0.39
     निम्न
    0.39
     Conv
    0.39
     let
    0.38
    !
    0.38
     Lesser
    0.38
     以下
    0.38
    Activations Density 0.002%

    No Known Activations