© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    al- names, clerics, city, Bible, ALS

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

    talked about avoiding obstacles

    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
    iliated
    0.56
    ých
    0.52
    acterial
    0.49
    C
    0.49
     क्रिस्ट
    0.48
    genus
    0.47
     টাই
    0.47
    ienen
    0.46
    ett
    0.46
    ode
    0.45
    POSITIVE LOGITS
    ند
    0.48
     말미
    0.48
     onders
    0.47
    窨
    0.47
    신도시
    0.47
     습
    0.46
     órgão
    0.45
    룩
    0.44
     transcend
    0.44
    澧
    0.44
    Activations Density 0.000%

    No Known Activations