© 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. 78677
    Prev
    Next
    INDEX
    Explanations

    therapy issues and problems

    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
     physiotherapy
    -0.89
    を含
    -0.84
    壩
    -0.82
     Polski
    -0.81
    Physio
    -0.81
     Physio
    -0.81
     Salam
    -0.80
     economists
    -0.79
    腥
    -0.79
    طط
    -0.78
    POSITIVE LOGITS
     issues
    1.27
     clients
    1.15
     couples
    1.08
     также
    1.02
    したい
    0.96
     grief
    0.95
     trauma
    0.94
    Clients
    0.94
     Glaubens
    0.92
    clients
    0.89
    Activations Density 0.030%

    No Known Activations