© 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. 201642
    Prev
    Next
    INDEX
    Explanations

    descriptions in notes

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

    policy and management concepts

    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
     zespół
    0.46
    ጊዜ
    0.44
    ianz
    0.43
    Zespół
    0.43
     Recruit
    0.43
     সমাধি
    0.42
    '
    0.42
     příst
    0.41
    ش
    0.41
     assembl
    0.40
    POSITIVE LOGITS
     المك
    0.45
    麦
    0.44
     смотре
    0.44
     طے
    0.44
     مك
    0.43
     مک
    0.43
     проведения
    0.42
    保温
    0.42
     сложных
    0.42
     रिया
    0.41
    Activations Density 0.000%

    No Known Activations