© 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. 24782
    Prev
    Next
    INDEX
    Explanations

    years of experience

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

    inscribe data

    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
    ű
    0.56
    adoc
    0.55
    ansen
    0.52
    üne
    0.52
    cher
    0.49
    ār
    0.49
    кра
    0.49
    ů
    0.49
    ilik
    0.48
    за
    0.48
    POSITIVE LOGITS
    ു
    0.54
     gels
    0.46
    ಪಡ
    0.44
     inférieures
    0.44
     entraî
    0.43
     vectorized
    0.42
    तियां
    0.42
     nucl
    0.41
     esigen
    0.41
     Aye
    0.41
    Activations Density 0.000%

    No Known Activations