© 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. 9902
    Prev
    Next
    INDEX
    Explanations

    covert op

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

    technical concepts and properties

    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
     S
    0.36
     K
    0.35
    ab
    0.34
    ut
    0.34
    ad
    0.33
     H
    0.32
    i
    0.31
    on
    0.31
    K
    0.31
     N
    0.30
    POSITIVE LOGITS
     vudd
    0.33
    𝘨
    0.33
    ਗਾ
    0.32
     motivic
    0.30
     함수의
    0.29
    羈
    0.29
     predic
    0.29
     joyous
    0.29
     largura
    0.29
     meromorphic
    0.28
    Activations Density 0.026%

    No Known Activations