© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172096
    Prev
    Next
    INDEX
    Explanations

    clients talking about services

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

    type in code

    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
    playback
    0.42
    condition
    0.40
    collar
    0.40
    ../../
    0.39
    ート
    0.39
    သောအ
    0.39
     infliction
    0.39
    active
    0.39
    ad
    0.39
     등에
    0.39
    POSITIVE LOGITS
     convers
    0.45
     Cré
    0.45
    ড়াই
    0.45
    龇
    0.45
     incroy
    0.44
     Cove
    0.43
     Loki
    0.43
    ódio
    0.43
     gesprek
    0.43
     நிச்ச
    0.43
    Activations Density 0.001%

    No Known Activations