© 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. 244898
    Prev
    Next
    INDEX
    Explanations

    severity and advice

    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
    л
    0.52
    the
    0.46
    लास
    0.43
    idio
    0.41
    u
    0.41
     diodes
    0.41
    uszko
    0.41
    非
    0.40
    лат
    0.40
    ographystyle
    0.40
    POSITIVE LOGITS
     경로
    0.57
     çoc
    0.55
     också
    0.54
     erhö
    0.53
     erneut
    0.53
     verwendet
    0.51
     ដ
    0.50
     البي
    0.49
     Höhe
    0.49
     Hö
    0.49
    Activations Density 0.000%

    No Known Activations