© 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. 196106
    Prev
    Next
    INDEX
    Explanations

    Non-corrosive, extant, washer

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

    expression and emotions

    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
    eezy
    0.56
     மூன்றாவது
    0.56
     концерт
    0.55
     Schauspiel
    0.52
     alleviating
    0.52
     Nhiều
    0.52
    祉
    0.50
     séances
    0.50
     sultry
    0.49
     श्रद्धांजलि
    0.49
    POSITIVE LOGITS
    un
    0.60
    x
    0.59
    on
    0.54
    乘
    0.52
    ul
    0.51
    OR
    0.51
    ’
    0.48
    ISO
    0.48
     for
    0.48
    RE
    0.48
    Activations Density 0.000%

    No Known Activations