© 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. 105695
    Prev
    Next
    INDEX
    Explanations

    'vell, poem

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

    examples and code

    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
     niez
    0.44
     unsurprisingly
    0.44
    N
    0.42
     sklep
    0.41
     chyba
    0.40
    เว็บไซต์
    0.40
     N
    0.39
    이면
    0.39
    詳細は
    0.39
     liczba
    0.39
    POSITIVE LOGITS
    гности
    0.47
    េទ
    0.47
    াত্য
    0.45
    genheim
    0.45
    тності
    0.45
     सप्त
    0.44
    anus
    0.43
    thorax
    0.43
     टाइगर
    0.43
     antaranya
    0.43
    Activations Density 0.001%

    No Known Activations