© 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. 31054
    Prev
    Next
    INDEX
    Explanations

    5 corners

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

    requires, implies, vary, more

    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
    ぞ
    0.45
    雑
    0.45
     Rakyat
    0.45
    ぎ
    0.42
    ໊
    0.41
    賂
    0.40
    slüman
    0.40
     spettacolo
    0.40
     Aboriginal
    0.40
    جس
    0.40
    POSITIVE LOGITS
     purus
    0.51
     requis
    0.45
     planer
    0.44
     {
    0.43
     certaines
    0.42
     bmp
    0.42
     gewählt
    0.41
     ብዙውን
    0.41
     የመጀመሪያ
    0.41
     sukses
    0.41
    Activations Density 0.000%

    No Known Activations