© 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. 170157
    Prev
    Next
    INDEX
    Explanations

    place names and related concepts

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

    prevents or enables actions

    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
     статистика
    0.55
    很多
    0.52
    咽
    0.48
    Fake
    0.47
    面
    0.46
     Анали
    0.46
     फर्जी
    0.46
    洨
    0.45
    殮
    0.45
    fake
    0.45
    POSITIVE LOGITS
     against
    0.60
     mampu
    0.60
     prevents
    0.59
     preventing
    0.57
     overlooking
    0.52
     🙌
    0.52
     enables
    0.51
     allows
    0.50
     oleh
    0.49
     perched
    0.49
    Activations Density 0.000%

    No Known Activations