© 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. 124634
    Prev
    Next
    INDEX
    Explanations

    age or status

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

    highlighting points or options

    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
     a
    0.55
    ко
    0.52
     her
    0.52
     mid
    0.52
     Union
    0.52
    yr
    0.50
     network
    0.50
     gas
    0.49
     y
    0.48
     image
    0.47
    POSITIVE LOGITS
    ირ
    0.51
     τὸν
    0.51
     розпо
    0.50
     پیچھے
    0.49
     მდ
    0.48
    currentCharacter
    0.48
     불구
    0.47
     отношению
    0.47
     detenido
    0.47
    ły
    0.46
    Activations Density 0.000%

    No Known Activations