© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9038
    Prev
    Next
    INDEX
    Explanations

    describing states or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    as
    0.47
    -
    0.46
    ay
    0.42
    ell
    0.41
    u
    0.41
    is
    0.41
    i
    0.40
    ّ
    0.40
    il
    0.39
    ut
    0.39
    POSITIVE LOGITS
     malice
    0.40
     mogę
    0.39
    avaju
    0.39
    오는
    0.38
     nuovamente
    0.37
     ці
    0.36
     opět
    0.36
     posso
    0.36
     môže
    0.36
     додат
    0.36
    Activations Density 0.536%

    No Known Activations