© 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. 160598
    Prev
    Next
    INDEX
    Explanations

    song, titled

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

    failure, error, or uncertainty

    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
    甲烷
    0.52
    楊
    0.46
     PRICE
    0.45
     평가
    0.45
     প্রয়োগ
    0.44
     three
    0.44
    焊接
    0.44
     minimise
    0.43
    티
    0.42
     minimising
    0.42
    POSITIVE LOGITS
     ating
    0.43
     gwar
    0.43
    atical
    0.43
     bisogna
    0.43
     númer
    0.42
     conquered
    0.42
     pard
    0.42
    pard
    0.42
     ถ้า
    0.42
    Ž
    0.41
    Activations Density 0.004%

    No Known Activations