© 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-16K
    7. 12467
    Prev
    Next
    INDEX
    Explanations

    religious or intellectual terms

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

    punctuation and technical terms

    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_16k_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
     </
    0.57
     filename
    0.53
     t
    0.53
    .</
    0.52
    filename
    0.49
     file
    0.48
     borne
    0.47
    invalidate
    0.46
     inbuilt
    0.45
     came
    0.44
    POSITIVE LOGITS
    াদক
    0.50
     Dose
    0.50
     চিকিৎসক
    0.50
     Beratung
    0.49
    镓
    0.48
     Bildern
    0.47
     Sanctuary
    0.46
    Maryland
    0.46
     Veter
    0.45
     STEELS
    0.45
    Activations Density 0.004%

    No Known Activations