© 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. 188898
    Prev
    Next
    INDEX
    Explanations

    judging people or things

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

    computational structures or organization

    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
    企
    0.46
    opens
    0.45
    元件
    0.43
     manc
    0.43
     Manit
    0.42
    マンス
    0.42
     .)
    0.42
    棈
    0.42
    nog
    0.42
    tikz
    0.41
    POSITIVE LOGITS
     endonuclease
    0.53
     organise
    0.52
     eradication
    0.50
     motherhood
    0.50
    បញ្ចូល
    0.50
     ఆరోగ్య
    0.48
    organised
    0.48
     биологи
    0.47
     बनाएं
    0.46
     katva
    0.46
    Activations Density 0.001%

    No Known Activations