© 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. 58539
    Prev
    Next
    INDEX
    Explanations

    overall good idea viral

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

    beautiful beaches, stunning islands

    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
    шила
    0.51
    琍
    0.50
    สำหรับ
    0.46
    Дан
    0.46
    Rae
    0.46
    Ꮢ
    0.46
    Vì
    0.46
    昨天
    0.45
    строва
    0.45
    맏
    0.45
    POSITIVE LOGITS
    jet
    0.49
     Fractions
    0.49
     FHD
    0.49
     FRA
    0.48
    umn
    0.48
     Fraction
    0.48
     Fractional
    0.47
     Vn
    0.47
     Government
    0.46
    inge
    0.46
    Activations Density 0.000%

    No Known Activations