© 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. 172502
    Prev
    Next
    INDEX
    Explanations

    regions, purpose, worth, district

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

    when condition is met

    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
    nee
    0.48
     tevé
    0.43
    协
    0.43
    less
    0.43
    lád
    0.42
     cohomology
    0.42
    conductivity
    0.42
     "
    0.41
    lf
    0.41
     jeweils
    0.41
    POSITIVE LOGITS
    ଂ
    0.50
    ತ್ರೆ
    0.44
    ઙ
    0.43
    妬
    0.43
    หรับ
    0.43
     plague
    0.43
    ड
    0.43
    वर्तमान
    0.42
    TabView
    0.42
    のと
    0.42
    Activations Density 0.000%

    No Known Activations