© 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. 200800
    Prev
    Next
    INDEX
    Explanations

    request accompanied

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

    QVBoxLayout

    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
    ဣ
    0.55
     δεδο
    0.54
     бренда
    0.54
     nape
    0.52
    頸
    0.52
     yú
    0.51
     agrí
    0.50
     disminución
    0.50
     sinister
    0.50
     riego
    0.49
    POSITIVE LOGITS
    ↵
    0.43
    elines
    0.42
    Ven
    0.42
     Chadwick
    0.42
    Eventually
    0.41
     Richards
    0.41
    die
    0.40
    Connell
    0.40
    Murphy
    0.40
    le
    0.39
    Activations Density 0.001%

    No Known Activations