© 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. 100415
    Prev
    Next
    INDEX
    Explanations

    building or exceptions

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

    contrasting phrases

    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
    sero
    0.52
    <unused346>
    0.49
    pov
    0.47
    pol
    0.46
     कों
    0.46
    azor
    0.46
    tta
    0.46
    ttino
    0.46
    gu
    0.46
    t
    0.46
    POSITIVE LOGITS
     drew
    0.52
     bass
    0.51
     pierced
    0.51
     experimentation
    0.50
     prosecution
    0.50
     মির
    0.49
     rosette
    0.49
     derivative
    0.48
     depressed
    0.48
     treasurer
    0.48
    Activations Density 0.002%

    No Known Activations