© 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. 197540
    Prev
    Next
    INDEX
    Explanations

    English text after non-English words

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

    allows, then, choose

    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
     paraphernalia
    0.49
     INDUSTRIAL
    0.42
     Industrial
    0.42
     vaporizer
    0.42
     insulated
    0.42
    httpRequest
    0.41
    insulated
    0.41
    懐
    0.41
     bulk
    0.40
     cigars
    0.39
    POSITIVE LOGITS
     artık
    0.53
     शुभेच्छा
    0.52
    ǐ
    0.44
     करुन
    0.44
    đe
    0.43
     त्यावर
    0.43
    考えて
    0.42
    ایی
    0.42
    astien
    0.42
    纷纷
    0.41
    Activations Density 0.000%

    No Known Activations