© 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. 244112
    Prev
    Next
    INDEX
    Explanations

    insurance replacement

    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
     Sosial
    0.50
     বিয়ে
    0.43
     Social
    0.41
     speckled
    0.41
    rustic
    0.41
    Social
    0.40
     brushes
    0.40
    扮
    0.40
     stimulation
    0.39
     Conservative
    0.39
    POSITIVE LOGITS
     procé
    0.58
     ար
    0.52
     οργαν
    0.50
     कवच
    0.50
     extrémités
    0.49
     correg
    0.48
     arranc
    0.48
     dirname
    0.47
    يدات
    0.46
     empêcher
    0.46
    Activations Density 0.000%

    No Known Activations