© 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. 84028
    Prev
    Next
    INDEX
    Explanations

    customize or modify settings

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

    these values

    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
     shuffle
    0.38
     صرف
    0.38
     overuse
    0.38
    жда
    0.37
    是一種
    0.37
    ⌨
    0.36
    削減
    0.36
    碼
    0.36
    ቷ
    0.36
    採用
    0.35
    POSITIVE LOGITS
     efect
    0.45
     bire
    0.44
    ikir
    0.43
     bilgiler
    0.43
     sair
    0.42
     kayıt
    0.42
     diri
    0.42
     தேதி
    0.41
     sami
    0.41
     proses
    0.40
    Activations Density 0.001%

    No Known Activations