© 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. 66201
    Prev
    Next
    INDEX
    Explanations

    specializes in certain domains

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

    risk, rich, format, specializing, diameter, initial

    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
     '
    0.50
     )
    0.49
     beiden
    0.46
     /
    0.44
     Greens
    0.43
     Wolver
    0.43
     "
    0.41
     Garn
    0.41
     %
    0.40
    /'
    0.40
    POSITIVE LOGITS
    ஜ்மஹால்
    0.53
    idur
    0.48
    〒
    0.48
    जारत
    0.46
    சார்
    0.46
    awing
    0.45
    ٴ
    0.45
    jaer
    0.45
    ಹಾರ
    0.45
    ETIC
    0.44
    Activations Density 0.001%

    No Known Activations