© 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. 193619
    Prev
    Next
    INDEX
    Explanations

    used or led

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

    classificationexamplesmathematicallinguistic variationspronunciationsspecificsabstract concepts

    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
     verg
    0.42
     dispersion
    0.42
     ,\
    0.41
    廬
    0.41
     bla
    0.41
    入手
    0.40
     бала
    0.40
     vasocon
    0.40
    |=|
    0.40
    你知道
    0.40
    POSITIVE LOGITS
    ią
    0.52
    aians
    0.50
    ozione
    0.50
    eduanya
    0.48
    Mathematics
    0.47
    DTDs
    0.46
    ına
    0.46
    inį
    0.46
    ções
    0.46
    ną
    0.45
    Activations Density 0.001%

    No Known Activations