© 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. 16859
    Prev
    Next
    INDEX
    Explanations

    dimensions and endings

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

    height, width, left, right attributes

    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
    <0x0D>
    0.45
    0.44
     And
    0.43
     Ouvrard
    0.42
    0.42
     sposób
    0.40
    </sub>
    0.40
     উদ্দেশ্যে
    0.40
    0.40
     ORDER
    0.40
    POSITIVE LOGITS
    atost
    0.47
    étrico
    0.42
    㩴
    0.42
    ทะเล
    0.41
    ५
    0.41
    і
    0.40
    մ
    0.40
    φος
    0.39
    etzes
    0.39
    吉
    0.39
    Activations Density 0.001%

    No Known Activations