© 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. 27461
    Prev
    Next
    INDEX
    Explanations

    hex color codes

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

    hexadecimal color codes

    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
     фарма
    0.53
     invertebr
    0.51
    왁
    0.46
     అంశ
    0.44
     종
    0.43
     شي
    0.43
    輥
    0.43
     enfermo
    0.43
     enfermos
    0.42
    <unused77>
    0.42
    POSITIVE LOGITS
     S
    0.66
     D
    0.63
     K
    0.61
     d
    0.61
    D
    0.61
     M
    0.59
    d
    0.58
    C
    0.55
    f
    0.54
     C
    0.53
    Activations Density 0.005%

    No Known Activations