© 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. 141926
    Prev
    Next
    INDEX
    Explanations

    daily talk

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

    Gap, Canvas, Seven, Repeat, sequence

    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
     ٢
    0.48
    сун
    0.47
    NG
    0.47
    Beer
    0.46
     у
    0.45
    Dur
    0.44
    Trademark
    0.44
     أول
    0.43
    oz
    0.43
    ₂
    0.43
    POSITIVE LOGITS
     परिवेश
    0.51
     lenguaje
    0.51
    ብሰ
    0.50
    }|^
    0.47
    ្ត
    0.46
    แพทย์
    0.45
    瘦
    0.45
     anillos
    0.45
    グラフ
    0.44
     график
    0.44
    Activations Density 0.003%

    No Known Activations