© 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. 210031
    Prev
    Next
    INDEX
    Explanations

    fermentation, separately, began

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

    directly links or focuses

    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
    ០
    0.54
    ri
    0.50
    ette
    0.49
    ﾘ
    0.49
    ૧
    0.47
     се
    0.46
    ETTE
    0.45
    С
    0.45
    Quote
    0.44
    ट
    0.44
    POSITIVE LOGITS
     atmospheric
    0.48
     governance
    0.47
     otherworldly
    0.46
     celestial
    0.46
     playerName
    0.44
     refrigerant
    0.44
     aerosol
    0.44
     ethereal
    0.43
     poisoned
    0.43
     microbiota
    0.43
    Activations Density 0.002%

    No Known Activations