© 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. 64591
    Prev
    Next
    INDEX
    Explanations

    Township Range sections

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

    translate languages

    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
     अध्ययन
    0.51
    이어
    0.48
    毆
    0.45
     அடை
    0.44
     महत्व
    0.44
    行动
    0.43
    貳
    0.43
    샨
    0.43
    冒险
    0.42
     প্রাধান্য
    0.42
    POSITIVE LOGITS
     (
    0.54
    ζεται
    0.48
    件
    0.47
    рите
    0.46
    GradientPanel
    0.45
    estyle
    0.45
    items
    0.44
     {
    0.44
    he
    0.44
     rela
    0.43
    Activations Density 0.001%

    No Known Activations