© 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. 51492
    Prev
    Next
    INDEX
    Explanations

    felled byJaggerone thingformidable instrument

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

    code, data, and current position

    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
    食べ
    0.53
    Lav
    0.53
     увиде
    0.52
    ເຂົ້າ
    0.52
    tìm
    0.51
     ધરા
    0.51
    gráf
    0.51
    飼
    0.50
     строительство
    0.50
    បង្
    0.49
    POSITIVE LOGITS
     lighthouse
    0.46
     is
    0.46
     liberty
    0.45
     laurea
    0.43
     Fet
    0.43
     RAC
    0.42
    रासत
    0.42
     formidable
    0.41
    ێنی
    0.41
     instrument
    0.41
    Activations Density 0.000%

    No Known Activations