© 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. 237789
    Prev
    Next
    INDEX
    Explanations

    carbon fibre

    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
    mazing
    0.49
     nucleotides
    0.46
    thereum
    0.45
    EN
    0.45
    REY
    0.43
    undur
    0.42
     $(<
    0.42
    𝟯
    0.42
    undi
    0.42
     inverno
    0.42
    POSITIVE LOGITS
     découvert
    0.50
     réelle
    0.48
    اسية
    0.47
     céré
    0.46
     waarop
    0.44
     فرهنگی
    0.44
     vooraf
    0.43
     déplacements
    0.42
    oost
    0.42
     vä
    0.42
    Activations Density 0.000%

    No Known Activations