© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129138
    Prev
    Next
    INDEX
    Explanations

    bracketed citations

    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
    																										
    -1.36
    																								
    -1.30
    殽
    -1.30
    																									
    -1.23
     revenu
    -1.21
     intervi
    -1.20
    ,«
    -1.20
     portait
    -1.20
    																							
    -1.20
     visite
    -1.19
    POSITIVE LOGITS
    1
    1.16
    2
    1.11
     and
    1.09
     numerous
    1.02
    ne
    1.02
     varied
    1.01
     polega
    1.01
     countless
    1.00
    r
    1.00
    ;
    0.98
    Activations Density 0.016%

    No Known Activations