© 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. 22-GEMMASCOPE-RES-131K
    7. 128613
    Prev
    Next
    INDEX
    Explanations

    code snippets and symbols

    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_22/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
     ruidos
    -1.45
    ␮
    -1.22
    ของ
    -1.18
     yılında
    -1.14
    Ĥ
    -1.13
    ğer
    -1.12
    unku
    -1.11
     pás
    -1.11
    வத
    -1.10
    ]^{
    -1.09
    POSITIVE LOGITS
     it
    1.20
    9
    1.19
    8
    1.16
    3
    1.14
    際には
    1.09
    7
    1.09
    6
    1.06
    1
    1.04
     each
    1.04
    4
    1.03
    Activations Density 0.058%

    No Known Activations