© 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. 123274
    Prev
    Next
    INDEX
    Explanations

    programmes and provision

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

    scientific and measurable domains

    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
     Type
    0.47
    nome
    0.46
     M
    0.45
     Formal
    0.45
    氰
    0.45
     Modo
    0.45
     Writing
    0.44
    Quando
    0.44
     così
    0.44
     Colour
    0.44
    POSITIVE LOGITS
    юнча
    0.55
    忑
    0.52
    atthaya
    0.52
    ısında
    0.51
    ığımız
    0.51
    owymi
    0.50
    ндагы
    0.50
     imposes
    0.49
    ței
    0.49
     членом
    0.49
    Activations Density 0.001%

    No Known Activations