© 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. 57639
    Prev
    Next
    INDEX
    Explanations

    business and daily life concepts

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

    features

    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
    تين
    0.46
    liness
    0.43
    পট
    0.42
    abundance
    0.42
    ”.
    0.41
    ll
    0.41
    \_
    0.40
    anners
    0.40
    RELL
    0.39
    cerpt
    0.39
    POSITIVE LOGITS
     ద్వ
    0.59
     કાર્ય
    0.52
     comunicação
    0.51
     一个
    0.50
     機能
    0.49
     δύο
    0.49
     የ
    0.47
     φυσ
    0.47
     روابط
    0.46
     γ
    0.46
    Activations Density 0.000%

    No Known Activations