© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39983
    Prev
    Next
    INDEX
    Explanations

    several other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -1.21
    急に
    -1.19
    を発見
    -1.10
     跳转至
    -1.10
    ↤
    -1.09
     valamint
    -1.09
     PERFECT
    -1.09
    пові
    -1.08
    铈
    -1.07
     misschien
    -1.06
    POSITIVE LOGITS
     other
    3.08
    其他
    1.96
     innych
    1.91
     других
    1.81
     others
    1.77
     diğer
    1.75
     its
    1.71
     anderen
    1.67
     otras
    1.65
    其他的
    1.65
    Activations Density 0.122%

    No Known Activations