© 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. 21591
    Prev
    Next
    INDEX
    Explanations

    crowd commotion

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

    explaining concepts and findings

    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
    TYPE
    0.51
    ⊟
    0.46
    IFIER
    0.45
    χ
    0.45
    τύ
    0.43
    ابعه
    0.43
     nemus
    0.43
    ר
    0.42
    EXAMPLE
    0.42
     నిర్
    0.42
    POSITIVE LOGITS
    োনো
    0.50
     पद्म
    0.48
     commotion
    0.48
    bender
    0.47
    colorful
    0.47
     marginalised
    0.46
     plein
    0.45
    شف
    0.45
    edere
    0.45
     असुर
    0.44
    Activations Density 0.000%

    No Known Activations