© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13671
    Prev
    Next
    INDEX
    Explanations

    ph/th words and exclamations

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

    Phase I, Phone number

    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_16k_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
    an
    1.08
    t
    0.99
    a
    0.93
    v
    0.93
    I
    0.87
    es
    0.86
    r
    0.86
    tól
    0.83
    z
    0.77
    er
    0.74
    POSITIVE LOGITS
    לו
    1.05
    ב
    1.02
    ب
    0.94
     profonde
    0.79
    দৈ
    0.77
    د
    0.75
     swarm
    0.73
     orbit
    0.73
     entière
    0.73
     celeb
    0.73
    Activations Density 2.838%

    No Known Activations