© 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. 66627
    Prev
    Next
    INDEX
    Explanations

    interface implementation object

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

    COM objects and components

    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
     пределах
    0.47
    ạ
    0.44
     Kxa
    0.42
    outline
    0.41
    бка
    0.41
     краё
    0.41
     Kxh
    0.40
    ाइए
    0.40
     `<=
    0.40
     செயல்
    0.40
    POSITIVE LOGITS
     milliard
    0.48
     discourses
    0.45
    玻璃
    0.44
     entities
    0.44
     মার্চ
    0.44
     Futuristic
    0.43
     poaching
    0.43
     frauds
    0.42
    λο
    0.41
    วิต
    0.41
    Activations Density 0.001%

    No Known Activations