© 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. 139025
    Prev
    Next
    INDEX
    Explanations

    numbered mathematical steps

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

    step-by-step reasoning

    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
    uiten
    0.50
    '))
    0.46
    Macrophages
    0.45
    רה
    0.44
    এরপর
    0.44
    ર્
    0.44
    や
    0.43
    يد
    0.42
    arsch
    0.42
    ູນ
    0.42
    POSITIVE LOGITS
     matemat
    0.54
     математи
    0.54
     Mathematic
    0.51
     եր
    0.49
     mathematicians
    0.49
     mathematic
    0.48
     единственный
    0.47
     maths
    0.46
     derivable
    0.46
     Mathematics
    0.45
    Activations Density 0.000%

    No Known Activations