© 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. 66219
    Prev
    Next
    INDEX
    Explanations

    exceptional examples

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

    child, response, growth, Bielefeld

    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
    #,
    0.45
    erti
    0.44
    γγ
    0.44
     Astrophysical
    0.43
    🤛
    0.43
    ług
    0.43
     мен
    0.42
    1
    0.42
    unj
    0.41
    ⁉
    0.41
    POSITIVE LOGITS
     интен
    0.59
     eksp
    0.52
     мани
    0.52
     беско
    0.46
    ivasena
    0.46
     arrange
    0.45
    ㄈ
    0.45
     employ
    0.44
     depred
    0.44
     қили
    0.44
    Activations Density 0.000%

    No Known Activations