© 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. 34647
    Prev
    Next
    INDEX
    Explanations

    how to, spoilers, specific dimensions

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

    introductions to explanations and examples

    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
    irr
    0.45
    winner
    0.45
    色的
    0.44
    affiliated
    0.43
    alike
    0.42
    <0x96>
    0.41
    half
    0.41
    awang
    0.41
    wig
    0.41
    one
    0.40
    POSITIVE LOGITS
     كيفية
    0.49
     spoiler
    0.45
     main
    0.43
     ways
    0.40
     respecto
    0.40
     rispetto
    0.40
     spoilers
    0.40
    ↓↓
    0.40
    >):
    0.40
     ():
    0.40
    Activations Density 0.016%

    No Known Activations