© 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. 179014
    Prev
    Next
    INDEX
    Explanations

    Lashes Lift

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

    information from earlier lost

    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
    s
    0.73
    P
    0.51
    aj
    0.50
    S
    0.47
    output
    0.44
    ald
    0.44
    下
    0.43
    als
    0.43
    F
    0.43
    q
    0.43
    POSITIVE LOGITS
     observé
    0.54
     hué
    0.53
    يتها
    0.53
     kiles
    0.50
     obstru
    0.50
     aún
    0.49
     মহাসচিব
    0.47
     hebre
    0.47
    шено
    0.47
    حي
    0.46
    Activations Density 0.000%

    No Known Activations