© 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. 143586
    Prev
    Next
    INDEX
    Explanations

    penalties and extra time

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

    solving equations, formulas, and math

    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
    rats
    0.42
    egna
    0.42
    ━━━━━━━━
    0.41
    탓
    0.40
     windmills
    0.40
    planung
    0.40
    uestro
    0.40
    封
    0.39
    closeup
    0.38
    শালী
    0.38
    POSITIVE LOGITS
    Референце
    0.43
     capacitances
    0.41
     résoudre
    0.40
     परीक्षाओं
    0.40
     μέσα
    0.39
     trận
    0.39
     collisional
    0.38
     técnicas
    0.37
     Sultan
    0.36
     illustrative
    0.36
    Activations Density 0.010%

    No Known Activations