© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191540
    Prev
    Next
    INDEX
    Explanations

    responsibilities, future outcomes, or consequences

    np_acts-logits-general · gemini-2.5-flash-lite

    technical SEO, China economy, water volume, neighbor relations, explicit statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     patients
    0.48
     of
    0.46
     while
    0.45
     woes
    0.44
     whom
    0.44
    >
    0.44
     germs
    0.43
     reasonable
    0.43
     doctor
    0.42
     heart
    0.42
    POSITIVE LOGITS
    สด
    0.50
     मिनिट
    0.49
     বৃহত্তম
    0.49
     ২টি
    0.49
    তম
    0.48
    ٢
    0.48
     ഇമാം
    0.48
     Изда
    0.48
     წარმო
    0.47
     종류
    0.47
    Activations Density 0.000%

    No Known Activations