© 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. 49257
    Prev
    Next
    INDEX
    Explanations

    Potiphar's house

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

    Joseph, slave, concubine

    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
     upotre
    0.51
    Below
    0.46
    怆
    0.45
    Notre
    0.44
    Op
    0.44
     Warhammer
    0.44
     Volta
    0.44
    Programme
    0.44
    পাতালে
    0.43
    ancien
    0.43
    POSITIVE LOGITS
     conclude
    0.44
    wett
    0.43
    ି
    0.43
     hypoallergenic
    0.42
     નિર્ણય
    0.40
    iply
    0.40
     enlighten
    0.39
     heifer
    0.39
     результат
    0.38
     disclose
    0.38
    Activations Density 0.001%

    No Known Activations