© 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. 67170
    Prev
    Next
    INDEX
    Explanations

    when asked or confronted

    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
     itali
    -0.85
     poème
    -0.85
     péché
    -0.84
     recensement
    -0.84
    icoot
    -0.84
     APPARATUS
    -0.83
     espoir
    -0.83
     estadounid
    -0.83
    șa
    -0.82
     kral
    -0.81
    POSITIVE LOGITS
     asked
    1.85
     questioned
    1.55
     questions
    1.51
     question
    1.48
     tempted
    1.31
     asks
    1.22
     confronted
    1.16
     worried
    1.13
     ask
    1.11
     curious
    1.09
    Activations Density 0.044%

    No Known Activations