© 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. 240043
    Prev
    Next
    INDEX
    Explanations

    Always choose, aim, territories

    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
     pensamientos
    0.47
    اداسی
    0.47
    への
    0.46
     speculations
    0.46
    㳯
    0.45
    古代
    0.45
    THREADS
    0.44
     disponible
    0.44
     conjectures
    0.43
    䁂
    0.43
    POSITIVE LOGITS
    0.56
    Commerce
    0.46
    Comedy
    0.46
    Pre
    0.45
     SOM
    0.45
    Prevent
    0.45
    다
    0.44
    Dom
    0.44
     दायरे
    0.44
    Values
    0.43
    Activations Density 0.001%

    No Known Activations