© 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. 217348
    Prev
    Next
    INDEX
    Explanations

    concluding remarks

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

    prints interface commands

    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
    ند
    0.55
    يم
    0.51
    كم
    0.48
    다
    0.47
    너
    0.46
    كر
    0.46
    دان
    0.45
    寸
    0.45
    ăm
    0.44
    ظم
    0.44
    POSITIVE LOGITS
     appendages
    0.59
     mów
    0.56
     commences
    0.52
    Concluding
    0.52
     jars
    0.52
     یق
    0.51
     adjustments
    0.50
     boundaries
    0.49
     calculates
    0.49
     &:
    0.49
    Activations Density 0.000%

    No Known Activations