© 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. 30612
    Prev
    Next
    INDEX
    Explanations

    No further, need to, less impact

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

    Multilingual technical/conceptual phrases

    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
    不允许
    0.52
    分为
    0.45
    ≥
    0.42
     isn
    0.41
     Supervisor
    0.41
    Supervisor
    0.41
    粘贴
    0.39
    PictureBox
    0.39
    组成
    0.39
    AndUpdate
    0.38
    POSITIVE LOGITS
    स्तव
    0.47
     harus
    0.45
    訃
    0.45
    ளுக்காக
    0.44
    acylglycer
    0.44
     नेट
    0.43
    druck
    0.43
     भूकंप
    0.43
    arono
    0.43
     смотре
    0.43
    Activations Density 0.000%

    No Known Activations