© 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. 86223
    Prev
    Next
    INDEX
    Explanations

    Balboa, markets, Holocene, local

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

    records, bacteria, blame, reviewer, method

    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
     звук
    0.52
     Approximate
    0.51
     เสียง
    0.49
    唦
    0.49
     Díaz
    0.48
    鬨
    0.48
     keySchedule
    0.48
     approxim
    0.47
    ണ്‍
    0.47
     renverse
    0.47
    POSITIVE LOGITS
    C
    0.50
    is
    0.47
    chil
    0.43
    RA
    0.43
     रु
    0.43
    Rud
    0.43
    DOCUMENT
    0.43
    IC
    0.42
    VI
    0.42
    cornell
    0.42
    Activations Density 0.000%

    No Known Activations