© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 30813
    Prev
    Next
    INDEX
    Explanations

    SMS, ICT, value, Glossary, edge, if

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

    import code

    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
    ،
    0.45
    ,
    0.44
     ،
    0.42
    ၊
    0.37
     أو
    0.37
    、
    0.34
    ؛
    0.33
     dvara
    0.33
    adı
    0.33
     města
    0.32
    POSITIVE LOGITS
    ListIterator
    0.32
    Ფ
    0.30
     tangled
    0.29
    לי
    0.29
     cameos
    0.29
    格外
    0.28
    ἆ
    0.28
    TG
    0.27
    שור
    0.27
     heuristics
    0.27
    Activations Density 0.000%

    No Known Activations