© 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. 188526
    Prev
    Next
    INDEX
    Explanations

    shortened URLs and links

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

    codes, numbers, or specific sequences

    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
     פרו
    0.41
    вались
    0.39
    ἠ
    0.39
     ALLE
    0.39
     прямо
    0.38
     उदासीन
    0.38
     которого
    0.38
    тили
    0.38
    转化为
    0.37
     दिखाई
    0.37
    POSITIVE LOGITS
    运营
    0.43
    Bone
    0.42
    PTO
    0.40
     Bone
    0.39
     superintend
    0.38
     শতাব্দ
    0.38
    })_{\
    0.38
    BOT
    0.36
    OI
    0.36
    Fifth
    0.36
    Activations Density 0.015%

    No Known Activations