© 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. 13029
    Prev
    Next
    INDEX
    Explanations

    addam, Godfather, unique identifiers

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

    introduction of concepts or specific entities

    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
    Σ
    0.46
     흡
    0.45
     their
    0.44
    И
    0.44
    Су
    0.43
    Из
    0.43
    슐
    0.42
     the
    0.42
    пи
    0.42
     сер
    0.42
    POSITIVE LOGITS
    addam
    0.47
     عشان
    0.45
    ী
    0.43
     Godfather
    0.43
     informacije
    0.43
     orphanage
    0.42
     eradication
    0.42
    ře
    0.42
     rozs
    0.42
     určit
    0.41
    Activations Density 0.001%

    No Known Activations