© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79038
    Prev
    Next
    INDEX
    Explanations

    offence carries

    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
     Wheeler
    -0.72
     椅
    -0.71
    ñas
    -0.69
    ⑰
    -0.69
    ddling
    -0.68
    írit
    -0.68
    萜
    -0.66
     buat
    -0.66
    ppur
    -0.66
     Akismet
    -0.66
    POSITIVE LOGITS
     carries
    4.81
     carry
    4.66
    carry
    3.98
     carrying
    3.84
     Carry
    3.81
    Carry
    3.72
     Carrying
    3.56
    Carrying
    3.53
    carrying
    3.50
     CARRY
    3.47
    Activations Density 0.170%

    No Known Activations