© 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. 64053
    Prev
    Next
    INDEX
    Explanations

    Associated Press and news reports

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

    news and events

    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
     Alemanha
    0.48
     TRANSPORTURI
    0.44
     milioane
    0.43
    intervals
    0.42
    螞
    0.42
     マル
    0.42
    歐洲
    0.40
     Alemania
    0.39
     Japón
    0.39
     Uda
    0.38
    POSITIVE LOGITS
     newspaper
    0.54
     Gazette
    0.47
     growth
    0.44
     Masses
    0.44
     District
    0.43
     newspapers
    0.43
     district
    0.42
    -,
    0.42
     website
    0.42
     legally
    0.41
    Activations Density 0.009%

    No Known Activations