© 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. 39298
    Prev
    Next
    INDEX
    Explanations

    unique, well known phrases

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

    ranges and combinations

    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
     Brug
    0.46
     comput
    0.45
     Michal
    0.44
     ו
    0.43
     അതിന്റെ
    0.43
     Schatten
    0.43
     Juillet
    0.43
     Vý
    0.43
     Wasser
    0.43
     Sche
    0.43
    POSITIVE LOGITS
    𝙉
    0.52
    颅
    0.50
    𝙀
    0.49
    iqueness
    0.48
    ଂ
    0.47
    群体
    0.45
    ёт
    0.44
    icolored
    0.44
    requencies
    0.44
    녔
    0.44
    Activations Density 0.000%

    No Known Activations