© 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. 101472
    Prev
    Next
    INDEX
    Explanations

    of win

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

    She, LinkedIn, concatenation, turning, storytelling

    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
    0
    0.64
    3
    0.64
    2
    0.62
    1
    0.59
    j
    0.57
    b
    0.57
    bs
    0.56
    os
    0.55
    D
    0.54
     to
    0.53
    POSITIVE LOGITS
     价
    0.58
     égales
    0.57
     corz
    0.55
     Estoy
    0.54
     prioridad
    0.54
     zéro
    0.53
    酺
    0.53
     promoción
    0.51
     réduite
    0.51
     każ
    0.50
    Activations Density 0.001%

    No Known Activations