© 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. 6356
    Prev
    Next
    INDEX
    Explanations

    ans additionally

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

    writing instructions and related items

    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
    on
    0.64
    ál
    0.55
    ע
    0.53
    áló
    0.48
    ╫
    0.47
    at
    0.47
    0.46
    髖
    0.46
    隱
    0.45
     aplicación
    0.45
    POSITIVE LOGITS
     verbatim
    0.54
     identifying
    0.50
     buttermilk
    0.48
     shippers
    0.48
     watchful
    0.48
     crystall
    0.47
     anybody
    0.46
     Sinhalese
    0.46
     hoping
    0.46
     abode
    0.46
    Activations Density 0.000%

    No Known Activations