© 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. 25951
    Prev
    Next
    INDEX
    Explanations

    expressing strong dislike

    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
    肉の
    -0.91
     a
    -0.90
    SIZ
    -0.87
    ">!
    -0.86
    ricane
    -0.84
     hopefully
    -0.84
    uszcz
    -0.83
     mischie
    -0.83
     カジュアル
    -0.81
    endish
    -0.81
    POSITIVE LOGITS
     being
    1.68
     anything
    1.65
     people
    1.40
     having
    1.34
     any
    1.33
     it
    1.20
     anyone
    1.20
     ANY
    1.16
    anything
    1.13
     seeing
    1.12
    Activations Density 0.052%

    No Known Activations