© 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. 164974
    Prev
    Next
    INDEX
    Explanations

    out of box overclocking

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

    counting and listing

    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
     Ramirez
    0.55
     كلا
    0.50
     chel
    0.50
     ha
    0.48
     McCl
    0.47
     dwie
    0.47
    蝮
    0.47
     শব্দের
    0.46
     Estoy
    0.46
     químicas
    0.46
    POSITIVE LOGITS
    financed
    0.50
    end
    0.48
    unload
    0.48
    ल्ले
    0.47
     मटे
    0.47
    Australia
    0.47
    planned
    0.47
    徴
    0.47
    up
    0.46
    allowed
    0.46
    Activations Density 0.000%

    No Known Activations