© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14059
    Prev
    Next
    INDEX
    Explanations

    android application selection

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

    language imports

    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_16k_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
     ተመሳሳይ
    0.45
    arity
    0.44
    類型
    0.43
    lines
    0.43
    "]
    0.42
    kates
    0.42
    StateException
    0.41
     ความ
    0.41
    к
    0.41
    similar
    0.40
    POSITIVE LOGITS
     adjusts
    0.39
    রায়
    0.38
     interrump
    0.38
     twe
    0.37
    启动
    0.37
    રા
    0.37
     ajustar
    0.35
     gerekti
    0.35
     accumulates
    0.35
     tercero
    0.35
    Activations Density 0.001%

    No Known Activations