© 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. 195675
    Prev
    Next
    INDEX
    Explanations

    then and supporting

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

    rights, sustainability, beyond

    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
    考
    0.51
     သူ့
    0.50
    流
    0.48
    𝚏
    0.48
    وره
    0.46
     水
    0.45
    HttpRequest
    0.45
    PushButton
    0.45
     hydraul
    0.45
    进
    0.45
    POSITIVE LOGITS
    brella
    0.48
     gleaned
    0.47
    daki
    0.46
     associativity
    0.45
    blica
    0.44
    ualaikum
    0.44
    ;?>
    0.44
     সংকোচন
    0.44
     exceeded
    0.43
     deli
    0.42
    Activations Density 0.000%

    No Known Activations