© 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. 33210
    Prev
    Next
    INDEX
    Explanations

    remained was had

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

    revenge fantasy and analysis

    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
     behe
    0.54
     فوټبال
    0.50
     rehab
    0.49
     salles
    0.49
     haya
    0.48
     সমঝো
    0.48
    ゾーン
    0.48
    6
    0.48
     جوړونکو
    0.48
     valiant
    0.47
    POSITIVE LOGITS
     З
    0.50
    нен
    0.49
    кет
    0.48
    χ
    0.48
     tomb
    0.47
    √(
    0.47
    svg
    0.46
    ליך
    0.46
    tyle
    0.44
     चीजों
    0.44
    Activations Density 0.000%

    No Known Activations