© 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. 41699
    Prev
    Next
    INDEX
    Explanations

    besides decisions

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

    decisions and ignoring agency

    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
    rom
    0.43
    nett
    0.43
    res
    0.42
    '
    0.42
     in
    0.42
     picture
    0.42
     С
    0.42
     wist
    0.42
     k
    0.41
    iko
    0.41
    POSITIVE LOGITS
     investigaciones
    0.50
     dumpster
    0.50
     decisions
    0.49
    最后的
    0.49
     নির্ধার
    0.48
     décide
    0.48
     givenChar
    0.47
     araşt
    0.47
     তারা
    0.47
     decisiones
    0.46
    Activations Density 0.000%

    No Known Activations