© 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. 37458
    Prev
    Next
    INDEX
    Explanations

    articles or, niche as, it would, your day

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

    similar tone or enthusiasm

    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
     የታ
    0.51
    a
    0.49
     Of
    0.47
     Some
    0.47
     İ
    0.47
     Archaeology
    0.47
    హం
    0.47
     Histor
    0.46
     Historical
    0.46
     Records
    0.46
    POSITIVE LOGITS
    муля
    0.48
    ➔
    0.47
    TIMES
    0.46
    ận
    0.45
    >{</
    0.45
     quyết
    0.44
    CLUB
    0.44
    -])
    0.43
    ercus
    0.43
    PARTY
    0.42
    Activations Density 0.000%

    No Known Activations