© 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. 88274
    Prev
    Next
    INDEX
    Explanations

    Lebanese hummus

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

    designed for installation

    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
    cm
    0.57
    с
    0.52
    H
    0.51
    ’
    0.49
    de
    0.48
    دو
    0.48
     cm
    0.47
    mn
    0.47
    '
    0.47
    р
    0.45
    POSITIVE LOGITS
     Infine
    0.47
    اط
    0.44
    느
    0.44
     abstr
    0.43
     impractic
    0.42
     granularity
    0.42
     impi
    0.41
     był
    0.41
     Rudolph
    0.41
     Equality
    0.40
    Activations Density 0.000%

    No Known Activations