© 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. 33304
    Prev
    Next
    INDEX
    Explanations

    joining ensemble, portrayed roles

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

    motherboard RAID

    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
    無論
    0.46
    一個人
    0.45
    婦
    0.45
     sämt
    0.44
     Thứ
    0.42
    頗
    0.42
    まぁ
    0.40
    বর্তমানে
    0.40
     ToolsVersion
    0.40
    جميع
    0.40
    POSITIVE LOGITS
    ar
    0.53
     新作
    0.49
     干
    0.47
     flagship
    0.46
    "<
    0.46
    ௐ
    0.46
     बचाने
    0.45
    iming
    0.45
     Packard
    0.45
     two
    0.44
    Activations Density 0.000%

    No Known Activations