© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3927
    Prev
    Next
    INDEX
    Explanations

    still remaining

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

    division, residuals, queues, grids, nonzero

    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
     dement
    0.40
     wholeheartedly
    0.38
    cumulative
    0.37
     foolish
    0.37
    年
    0.36
     adopter
    0.35
     Increasingly
    0.35
    博
    0.35
    ww
    0.35
    Chloro
    0.35
    POSITIVE LOGITS
     nonzero
    0.42
     quando
    0.40
    nonzero
    0.38
     nahin
    0.38
    inite
    0.37
     restante
    0.37
     trama
    0.37
     não
    0.37
     kuten
    0.36
    aniti
    0.36
    Activations Density 0.000%

    No Known Activations