© 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. 247617
    Prev
    Next
    INDEX
    Explanations

    opportunity posed

    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
    탬
    0.57
     pengalaman
    0.52
     declara
    0.47
     mision
    0.47
     antigu
    0.47
     ombil
    0.47
    ント
    0.46
     internacional
    0.46
     transplants
    0.46
     akum
    0.46
    POSITIVE LOGITS
     Alka
    0.46
    ewo
    0.43
     Kg
    0.43
     hilly
    0.43
    (-\
    0.42
    并在
    0.42
     Alkal
    0.41
    Widgets
    0.41
     Egan
    0.40
     Compress
    0.40
    Activations Density 0.001%

    No Known Activations