© 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. 244244
    Prev
    Next
    INDEX
    Explanations

    harm, damage, sorry, multilingual, mixed-language

    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
     golf
    0.47
     Golf
    0.47
    以
    0.46
     equestrian
    0.46
     golfing
    0.44
     becomes
    0.44
    тков
    0.44
    成為
    0.43
    ధాన
    0.43
    擔任
    0.43
    POSITIVE LOGITS
     हानि
    0.64
     dommages
    0.53
     চূ
    0.53
     hémorro
    0.52
     सॉरी
    0.50
    .‏
    0.50
     кіль
    0.49
    けど
    0.49
    zec
    0.48
     ھ
    0.48
    Activations Density 0.001%

    No Known Activations