© 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. 235073
    Prev
    Next
    INDEX
    Explanations

    independence percentage II novel illegal anti-

    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
     törté
    0.44
     críticas
    0.43
    िवे
    0.43
    εργ
    0.42
    িনবার্গ
    0.41
    doesn
    0.41
    ઞ
    0.41
    usher
    0.40
     passeio
    0.40
    STE
    0.39
    POSITIVE LOGITS
    ally
    0.48
     antifungal
    0.47
    omicide
    0.46
    avo
    0.46
    apot
    0.45
     곳
    0.44
    ante
    0.43
     illegal
    0.42
    cki
    0.42
     antibiotic
    0.42
    Activations Density 0.001%

    No Known Activations