© 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. 150258
    Prev
    Next
    INDEX
    Explanations

    services and locations

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

    finding substrings

    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
     우
    0.53
    upt
    0.49
     项目
    0.49
     其中
    0.48
    دت
    0.47
     ක
    0.47
     دانش
    0.47
     계획
    0.47
    ust
    0.47
     인수
    0.46
    POSITIVE LOGITS
     pretzels
    0.49
     civilizations
    0.45
     behaved
    0.44
     behaving
    0.44
    МА
    0.44
     लौटने
    0.44
    RTC
    0.43
    ઈ
    0.43
    ícula
    0.42
    ளையும்
    0.41
    Activations Density 0.002%

    No Known Activations