© 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. 81701
    Prev
    Next
    INDEX
    Explanations

    phrases with specific follow-ups

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

    biological, player, green, masters, transform, *, back, standard, driven, pamphlets

    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
    Negative Logits
    CameraButton
    0.46
    ColorBit
    0.46
     cercare
    0.44
    Affected
    0.44
     格
    0.44
     câmera
    0.43
    áját
    0.43
    гри
    0.43
    ľad
    0.43
     amplio
    0.42
    POSITIVE LOGITS
    游戏
    0.47
    ี
    0.45
    ཉ
    0.44
    团体
    0.44
    崩溃
    0.43
    게임
    0.43
    j
    0.43
    游戏中
    0.43
    疑问
    0.43
    สำเร็จ
    0.43
    Activations Density 0.000%

    No Known Activations