© 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. 117046
    Prev
    Next
    INDEX
    Explanations

    of, when, is, ask, half, I, production

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

    technical details and functionality

    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
    peter
    0.48
    nivers
    0.47
    kona
    0.47
    ther
    0.46
    Robert
    0.45
     Ther
    0.44
    s
    0.44
    Funcion
    0.44
     adapt
    0.43
    paul
    0.43
    POSITIVE LOGITS
     pulau
    0.48
    ເຕ
    0.46
    ཤ
    0.46
     pertes
    0.46
     schizophren
    0.44
     왼쪽
    0.44
    เท
    0.43
     모든
    0.43
     impairments
    0.43
    тит
    0.43
    Activations Density 0.000%

    No Known Activations