© 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. 46719
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    security and infrastructure responsibility

    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
     pavilions
    0.51
     ballads
    0.50
    대로
    0.49
    illar
    0.46
     ejempl
    0.46
     Motorola
    0.46
    abell
    0.45
    ਂ
    0.45
     medallions
    0.45
    鶚
    0.45
    POSITIVE LOGITS
    过程中
    0.52
    炼
    0.47
    边
    0.47
    Grow
    0.46
    Paged
    0.46
    лоба
    0.45
    να
    0.45
    Photos
    0.45
    hé
    0.45
    сті
    0.44
    Activations Density 0.000%

    No Known Activations