© 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. 225546
    Prev
    Next
    INDEX
    Explanations

    problem/bruising/importance/two

    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
     किं
    0.45
    မ္
    0.45
    人工智能
    0.44
    缬
    0.43
    瀋
    0.42
    лябин
    0.42
     దీ
    0.41
    成熟
    0.41
    介入
    0.41
    lenül
    0.40
    POSITIVE LOGITS
     tricycle
    0.53
     voter
    0.48
     motoc
    0.48
     będzie
    0.45
     competencia
    0.44
     ponytail
    0.44
    ى
    0.44
     poncho
    0.44
     coinbase
    0.44
     pu
    0.43
    Activations Density 0.001%

    No Known Activations