© 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. 181148
    Prev
    Next
    INDEX
    Explanations

    poor people

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

    seq command for sequences

    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
    Object
    0.45
    dicke
    0.44
    Gross
    0.44
     मांगी
    0.44
    As
    0.43
    February
    0.43
    I
    0.43
    Andrew
    0.43
    亣
    0.43
    ังกฤษ
    0.43
    POSITIVE LOGITS
    手游
    0.47
     vendeurs
    0.46
     ospiti
    0.46
     direta
    0.46
     addirittura
    0.46
    GOND
    0.45
     ponsel
    0.45
     maritime
    0.44
     granularity
    0.44
     comunale
    0.44
    Activations Density 0.002%

    No Known Activations