© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 189044
    Prev
    Next
    INDEX
    Explanations

    honorable servicemen

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

    input/output specifications

    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
    ak
    0.58
    ic
    0.52
    atik
    0.52
    ik
    0.51
    ies
    0.50
    Ак
    0.50
    at
    0.50
    }:
    0.49
    ivity
    0.47
    icist
    0.46
    POSITIVE LOGITS
     noticeably
    0.54
     podrá
    0.49
    부가
    0.49
     Yoo
    0.49
     오후
    0.48
     mutta
    0.47
    ००
    0.47
     currentTime
    0.46
     pointA
    0.46
    ০০
    0.45
    Activations Density 0.001%

    No Known Activations