© 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. 162184
    Prev
    Next
    INDEX
    Explanations

    public and, groups of, way to

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

    functionality and interaction

    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
    няка
    0.49
    jackson
    0.45
    vrage
    0.44
    क्स्ट
    0.43
    линд
    0.43
    ᅯ
    0.43
    acceptance
    0.43
    serialization
    0.42
    determination
    0.42
    zah
    0.42
    POSITIVE LOGITS
     visions
    0.57
     satisfying
    0.53
     simulate
    0.53
     hammers
    0.51
     pdelay
    0.50
     glories
    0.49
     congr
    0.49
    。[
    0.49
     nachos
    0.48
     gol
    0.46
    Activations Density 0.000%

    No Known Activations