© 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. 126253
    Prev
    Next
    INDEX
    Explanations

    financial statements or stock information

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

    multilingual or non-Latin scripts

    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
     Transportation
    0.54
     ||
    0.46
     Mercury
    0.46
     måtte
    0.45
     cancers
    0.44
     birthdays
    0.43
    ward
    0.42
    Rx
    0.42
    Normalized
    0.41
    SXml
    0.41
    POSITIVE LOGITS
    ပ
    0.54
    ین
    0.54
    プロセス
    0.53
    ב
    0.53
    カ
    0.50
     concentración
    0.50
    ತ
    0.50
    גר
    0.49
     mejora
    0.49
    ە
    0.49
    Activations Density 0.000%

    No Known Activations