© 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. 136567
    Prev
    Next
    INDEX
    Explanations

    "This is" or "such a"

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

    imagine scenarios and lists

    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
    ürnberg
    0.50
    úng
    0.47
    邇
    0.46
    elevationMap
    0.44
    endien
    0.44
    lineContainer
    0.43
    朔
    0.43
    녓
    0.43
    গৃহ
    0.42
    كية
    0.42
    POSITIVE LOGITS
     yli
    0.51
     ос
    0.50
     widz
    0.48
    ACON
    0.48
     AQ
    0.46
     Likes
    0.45
     ترى
    0.45
     calculating
    0.45
     stage
    0.45
    시아
    0.44
    Activations Density 0.001%

    No Known Activations