© 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. 7670
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

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

    list sorting algorithms

    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
    CameraButton
    0.41
    યર
    0.37
    erdapat
    0.37
    auern
    0.37
    éb
    0.36
    BackgroundColor
    0.36
    Ŏ
    0.35
    ект
    0.34
    ็อก
    0.34
    ௐ
    0.34
    POSITIVE LOGITS
     Bình
    0.38
     tình
    0.37
     college
    0.35
     bình
    0.35
     gạo
    0.35
     linh
    0.35
     Ayurvedic
    0.35
     Kishan
    0.35
     OSCE
    0.34
     lương
    0.34
    Activations Density 0.000%

    No Known Activations