© 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. 107223
    Prev
    Next
    INDEX
    Explanations

    bulletin concerning

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

    Acknowledgement, mild emotion, possibility

    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
     devast
    0.56
     globules
    0.56
     ಕೂದಲ
    0.56
     fibrils
    0.55
    rind
    0.54
     ವಿಷ
    0.53
    𒌨
    0.52
     PWMB
    0.52
    ুরের
    0.52
    mato
    0.50
    POSITIVE LOGITS
      
    0.45
     […]
    0.45
    是
    0.43
    0.43
    h
    0.41
    社交
    0.39
    فن
    0.39
    hp
    0.39
    ف
    0.38
    مر
    0.38
    Activations Density 0.000%

    No Known Activations