© 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. 69471
    Prev
    Next
    INDEX
    Explanations

    hosting solutions

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

    seasons and languages

    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
     koment
    0.54
    ტიკ
    0.49
    Ꮯ
    0.49
    琤
    0.48
     المغ
    0.48
    Ꮇ
    0.47
    ঝো
    0.46
     exchanging
    0.46
     అమె
    0.44
    Ⲡ
    0.44
    POSITIVE LOGITS
     presentes
    0.52
     gui
    0.49
    eksiyon
    0.47
    oribus
    0.46
    division
    0.45
     conspicuously
    0.44
    ibold
    0.43
     disposiciones
    0.43
     \
    0.43
     बचाव
    0.43
    Activations Density 0.001%

    No Known Activations