© 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. 45473
    Prev
    Next
    INDEX
    Explanations

    various common words

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

    constant boundaries or relationships

    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
    ᱙
    0.50
     arterial
    0.50
     carotid
    0.48
     elephant
    0.46
     intracranial
    0.46
     ventricular
    0.46
     купи
    0.46
     curta
    0.46
    ated
    0.45
     artery
    0.45
    POSITIVE LOGITS
    岭
    0.50
    FAO
    0.49
    狱
    0.48
    路线
    0.45
    烔
    0.45
     쉬
    0.43
    köz
    0.43
    մ
    0.43
    ilyen
    0.43
     setNew
    0.43
    Activations Density 0.001%

    No Known Activations