© 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. 100973
    Prev
    Next
    INDEX
    Explanations

    mode, applications, specifically, jump

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

    escalating incidents, highly evolved, profoundly altering

    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
     l
    0.50
     leaching
    0.49
    ordo
    0.47
    inds
    0.47
     odv
    0.47
     GSK
    0.46
     Wochschr
    0.46
     भने
    0.46
    imshow
    0.45
     gs
    0.44
    POSITIVE LOGITS
    えます
    0.49
    。
    0.46
    ్యా
    0.46
    。（
    0.45
    진다
    0.45
    피
    0.44
    ۔
    0.44
    ។
    0.44
    ますが
    0.43
    ਐ
    0.43
    Activations Density 0.001%

    No Known Activations