© 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. 151423
    Prev
    Next
    INDEX
    Explanations

    warnings and consequences

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

    layers, questions, sprouts, have

    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
     operations
    0.48
    inom
    0.48
     experi
    0.45
     t
    0.44
    inus
    0.44
    ለኛ
    0.43
     Dist
    0.43
     fator
    0.42
     n
    0.42
     plants
    0.42
    POSITIVE LOGITS
    heiros
    0.49
    حدیث
    0.49
    அது
    0.49
    ukiyoe
    0.49
     Biotechnology
    0.49
    नीत
    0.49
     Großbritannien
    0.48
    Moscow
    0.47
    Seoul
    0.47
    ரிக்க
    0.46
    Activations Density 0.001%

    No Known Activations