© 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. 181829
    Prev
    Next
    INDEX
    Explanations

    constructor definitions and initializations

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

    constructor

    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
    Mot
    0.50
    DNA
    0.44
    ツイ
    0.44
    መን
    0.44
    Script
    0.43
    Pasta
    0.43
    谚
    0.43
    主題
    0.43
    eyen
    0.43
    ಉ
    0.42
    POSITIVE LOGITS
     WITH
    0.52
     Gases
    0.51
     когато
    0.48
     gases
    0.46
     BUN
    0.46
     initializes
    0.45
     CASES
    0.44
     GAS
    0.44
     OFFER
    0.44
     bé
    0.43
    Activations Density 0.002%

    No Known Activations