© 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. 241020
    Prev
    Next
    INDEX
    Explanations

    their intent

    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
    aster
    0.53
    iphone
    0.48
    ilet
    0.46
    sc
    0.46
    about
    0.46
    ids
    0.46
    ball
    0.46
    焖
    0.44
    acid
    0.44
    achen
    0.44
    POSITIVE LOGITS
     również
    0.61
     ALSO
    0.53
     Krista
    0.50
     ebenfalls
    0.49
     in
    0.48
    ส่วน
    0.48
     RenderTexture
    0.48
     tiež
    0.48
     полный
    0.47
     njima
    0.47
    Activations Density 0.002%

    No Known Activations