© 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. 137903
    Prev
    Next
    INDEX
    Explanations

    prospective properties or townhouses

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

    focuses, learns, maintains, bit more

    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
    SELECTOR
    0.47
     outspoken
    0.46
     Selector
    0.45
    \{
    0.45
     Cyber
    0.45
     GestureDetector
    0.44
     Certificate
    0.43
    talk
    0.43
     Secret
    0.43
     Geom
    0.43
    POSITIVE LOGITS
    endis
    0.52
     एग्जामिनेशन
    0.52
    ᒐ
    0.48
    unfinished
    0.46
    avr
    0.45
    imak
    0.45
     الا
    0.45
    ariums
    0.45
     emptiness
    0.44
     invitados
    0.44
    Activations Density 0.001%

    No Known Activations