© 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. 197447
    Prev
    Next
    INDEX
    Explanations

    wine, colors, mobile, regional, results

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

    outcome registration fashion

    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
     神
    0.47
     complied
    0.46
     encoder
    0.45
    機器
    0.45
     adhesive
    0.44
     stepping
    0.44
    服务
    0.43
    游戏
    0.42
     complying
    0.42
    აწილ
    0.42
    POSITIVE LOGITS
    oit
    0.52
     macam
    0.49
     testAvg
    0.49
     طلاب
    0.48
    聳
    0.48
    ASSI
    0.48
    วี
    0.47
     Bertrand
    0.47
     toca
    0.47
     tocar
    0.46
    Activations Density 0.000%

    No Known Activations