© 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. 200775
    Prev
    Next
    INDEX
    Explanations

    known as KD(Killer

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

    scope, quick, Humanity, Roots, motivation

    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
             
    0.46
     rescues
    0.42
     sleepy
    0.41
    /
    0.41
    &
    0.41
     shepherds
    0.41
     layouts
    0.40
     horr
    0.40
     adventurous
    0.40
    䀖
    0.40
    POSITIVE LOGITS
    Become
    0.55
    াদ্র
    0.47
     втра
    0.46
    Analyser
    0.45
    Dont
    0.45
    usstsein
    0.45
     Become
    0.45
    orius
    0.45
    Analytical
    0.44
    ोटी
    0.44
    Activations Density 0.000%

    No Known Activations