© 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. 70611
    Prev
    Next
    INDEX
    Explanations

    capitalization, accents, and special characters

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

    acronyms and acrostics

    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
     bubbles
    0.45
     নৃত
    0.44
     imagen
    0.42
     spas
    0.41
     대회
    0.41
     игровой
    0.41
     animations
    0.40
     党
    0.40
    cohols
    0.40
     unbalanced
    0.40
    POSITIVE LOGITS
    concern
    0.43
    យៈ
    0.43
     entwickelte
    0.43
    網友
    0.41
    wrote
    0.40
    Minister
    0.39
     rozpoc
    0.39
    ໝ
    0.39
     Minister
    0.38
    ,“
    0.38
    Activations Density 0.000%

    No Known Activations