© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27461
    Prev
    Next
    INDEX
    Explanations

    talk to

    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
     appartiennent
    -1.34
     anjo
    -1.20
     peixes
    -1.13
     pittores
    -1.09
    Vlast
    -1.09
     всеки
    -1.07
    呶
    -1.07
     apparaissent
    -1.05
     dentes
    -1.05
     grec
    -1.05
    POSITIVE LOGITS
     not
    1.16
     gets
    1.01
     as
    1.01
     isn
    1.00
     it
    1.00
     terror
    0.99
     putting
    0.99
     at
    0.98
     puts
    0.98
    :
    0.97
    Activations Density 0.009%

    No Known Activations