© 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. 43714
    Prev
    Next
    INDEX
    Explanations

    specific phrases and collocations

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

    meticulous research, specific gear

    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
    t
    0.48
     Twist
    0.45
     dépour
    0.44
    twist
    0.42
    스템
    0.42
     without
    0.42
     суть
    0.42
     covalently
    0.41
     coaxial
    0.41
    ฺ
    0.41
    POSITIVE LOGITS
    jaar
    0.48
    bben
    0.48
     ঘটে
    0.46
    NgramModel
    0.43
    Officer
    0.43
     hadden
    0.43
    edores
    0.42
     chamado
    0.42
    ঈদ
    0.42
    Values
    0.42
    Activations Density 0.000%

    No Known Activations