© 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. 2943
    Prev
    Next
    INDEX
    Explanations

    like Instagram posts

    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
     rs
    -0.87
    EXCEPT
    -0.82
    ването
    -0.82
     control
    -0.81
     vary
    -0.80
     opaque
    -0.79
     Ги
    -0.79
     rosa
    -0.79
     pais
    -0.79
     RG
    -0.77
    POSITIVE LOGITS
     Liked
    0.97
    喜歡
    0.92
     liked
    0.81
     Instagram
    0.79
     Likes
    0.79
    ℙ
    0.78
     gustó
    0.77
     resuscitation
    0.77
    ...');
    0.77
     stehenden
    0.75
    Activations Density 0.002%

    No Known Activations