© 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. 237139
    Prev
    Next
    INDEX
    Explanations

    Prophets and foreign words

    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
     recrut
    0.48
     육
    0.46
    链路
    0.45
    এছ
    0.45
    쾰
    0.45
     caries
    0.44
     sleeveless
    0.43
    нија
    0.43
     동물
    0.43
     spermato
    0.43
    POSITIVE LOGITS
    tiin
    0.44
    ِب
    0.43
    endo
    0.43
     Prophets
    0.42
    Into
    0.42
     Honestly
    0.42
    हिंदी
    0.41
     Into
    0.41
    ihin
    0.41
    ían
    0.40
    Activations Density 0.001%

    No Known Activations