© 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. 134480
    Prev
    Next
    INDEX
    Explanations

    boot camp, craft industry, doubles

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

    concepts and state-of-the-art understanding

    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
    r
    0.54
    n
    0.51
    p
    0.51
    S
    0.50
    .
    0.49
    an
    0.49
    </h3>
    0.48
    wolf
    0.47
    t
    0.47
    mathrm
    0.46
    POSITIVE LOGITS
    會議
    0.55
     rafting
    0.51
     conferencing
    0.48
     tronco
    0.47
     conferences
    0.47
     antidepress
    0.47
    ଼
    0.47
    DrvGPIO
    0.46
     MEETING
    0.46
     counselling
    0.46
    Activations Density 0.001%

    No Known Activations