© 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. 224602
    Prev
    Next
    INDEX
    Explanations

    location, Country, Jung, small, appetite, store

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

    sexual content or safety concerns

    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
    ري
    0.57
     Standards
    0.50
     Backyard
    0.50
    িতে
    0.50
    ర్
    0.48
    uran
    0.47
    髹
    0.47
    تس
    0.46
    Rescue
    0.46
     Crime
    0.46
    POSITIVE LOGITS
     newLine
    0.57
     velvety
    0.53
     delicately
    0.51
     expertly
    0.50
     curls
    0.50
     dulces
    0.50
     preds
    0.50
     clothed
    0.50
     humidifier
    0.49
     beautifully
    0.49
    Activations Density 0.000%

    No Known Activations