© 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. 49183
    Prev
    Next
    INDEX
    Explanations

    following parentheses or the word the

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

    ARM, Dolphin, created, organize, remove

    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
    КТ
    0.50
     Tax
    0.46
    kopf
    0.45
    طف
    0.43
    ва
    0.42
    ナ
    0.42
    Tax
    0.42
    ઊ
    0.42
    ба
    0.41
    颀
    0.41
    POSITIVE LOGITS
     detects
    0.47
    esty
    0.46
     walkways
    0.46
    បង្
    0.46
     डिटे
    0.46
    amatan
    0.45
    !)
    0.45
     detecting
    0.45
     serviceable
    0.44
     detectar
    0.44
    Activations Density 0.000%

    No Known Activations