© 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. 157922
    Prev
    Next
    INDEX
    Explanations

    . use should updated book members prospective milestone

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

    vocoder, check to, Pass, disgust, socket

    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
    f
    0.46
    ្ល
    0.45
    毎週
    0.45
     \
    0.44
     Preprint
    0.44
     Erst
    0.44
    oths
    0.41
    VERE
    0.41
     heres
    0.40
     (_.
    0.40
    POSITIVE LOGITS
     receptacle
    0.48
    лок
    0.48
    Xcode
    0.47
     dehydration
    0.46
     moistened
    0.46
     quibusdam
    0.45
     машинасы
    0.45
    乆
    0.45
     chauffage
    0.44
     macchina
    0.44
    Activations Density 0.001%

    No Known Activations