© 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. 59050
    Prev
    Next
    INDEX
    Explanations

    recognizes capital letters

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

    automatic detection and action

    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
     їх
    0.46
     پوری
    0.44
    ަކ
    0.42
     پورا
    0.42
     их
    0.42
    ifera
    0.42
    å
    0.41
     ಅವರ
    0.40
    🏂
    0.40
    дин
    0.40
    POSITIVE LOGITS
     recognizes
    0.81
     recognises
    0.72
     detects
    0.66
     calculates
    0.65
     recognize
    0.64
     recognise
    0.62
     insists
    0.62
     tells
    0.61
     использует
    0.60
     knows
    0.59
    Activations Density 0.093%

    No Known Activations