© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91316
    Prev
    Next
    INDEX
    Explanations

    stud boy

    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_34/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
    Needs
    -0.79
    нув
    -0.73
    дим
    -0.73
     aDecoder
    -0.72
    Salud
    -0.72
     ActivatedRoute
    -0.72
    ֔
    -0.71
     EFF
    -0.71
     Eff
    -0.71
     SAC
    -0.70
    POSITIVE LOGITS
    ="+
    1.51
     =
    1.29
    ="
    1.25
    =",
    1.24
    =");
    1.22
    ='
    1.20
    =
    1.13
     $=
    1.10
    =>
    1.09
    =\
    1.07
    Activations Density 0.071%

    No Known Activations