© 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. 157130
    Prev
    Next
    INDEX
    Explanations

    common introductory phrases

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

    requests for songs

    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
    ケート
    0.46
    分析
    0.43
     Zentr
    0.43
    ла
    0.43
    中美
    0.42
    ý
    0.41
     Analyse
    0.41
    य
    0.41
    سن
    0.40
    Newly
    0.40
    POSITIVE LOGITS
     cognac
    0.51
     polarizer
    0.51
     isos
    0.50
     maus
    0.49
     apnea
    0.48
     outro
    0.48
     tomato
    0.47
     popup
    0.47
     seria
    0.47
     turquoise
    0.46
    Activations Density 0.001%

    No Known Activations