© 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. 201006
    Prev
    Next
    INDEX
    Explanations

    or maps

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

    but my systems

    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
     ataupun
    0.40
     været
    0.40
    ,
    0.39
     ök
    0.39
    '
    0.39
     Palmer
    0.39
     atau
    0.39
     características
    0.39
     Congregation
    0.38
     intolerant
    0.38
    POSITIVE LOGITS
    잽
    0.51
    海南
    0.51
    ატ
    0.48
     বহুম
    0.48
     শ্রেণ
    0.48
    悶
    0.47
    なん
    0.46
    🔧
    0.46
    ACING
    0.45
     બહાર
    0.44
    Activations Density 0.000%

    No Known Activations