© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12452
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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
     trd
    -1.11
     salido
    -1.09
    <tbody>
    -1.05
    “,
    -1.04
    знание
    -1.03
    DDR
    -1.02
     många
    -1.02
     inginkan
    -1.02
     kebiasaan
    -1.02
     condol
    -1.01
    POSITIVE LOGITS
     said
    3.03
    บอก
    1.57
     says
    1.51
     saying
    1.50
     say
    1.39
     nói
    1.36
    说
    1.30
     state
    1.27
     also
    1.27
     further
    1.24
    Activations Density 0.056%

    No Known Activations