© 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. 141679
    Prev
    Next
    INDEX
    Explanations

    words followed by specific terms

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

    missing, failing, or single

    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
     straks
    0.48
     csak
    0.47
     薄
    0.46
     bibliothèque
    0.45
     vå
    0.44
     kapat
    0.44
     forbids
    0.44
     眼
    0.44
     ပြ
    0.43
    㕩
    0.43
    POSITIVE LOGITS
    ១
    0.54
    wear
    0.52
    data
    0.51
    plate
    0.50
    ۱
    0.50
    Auto
    0.49
    1
    0.49
     culminating
    0.47
    delta
    0.46
    LAN
    0.46
    Activations Density 0.000%

    No Known Activations