© 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. 34158
    Prev
    Next
    INDEX
    Explanations

    alternative for

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

    IQ, HR, management, tests

    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
     ウォ
    0.50
     ಯ
    0.49
     み
    0.47
    Italia
    0.47
     notizie
    0.46
     статье
    0.46
     ブ
    0.45
    記事
    0.45
     العلام
    0.45
    ᱩ
    0.44
    POSITIVE LOGITS
    ні
    0.53
    ker
    0.47
     escolh
    0.46
     Turbulent
    0.46
    ಂತಿ
    0.46
    фіка
    0.45
    *
    0.45
    فی
    0.44
    veil
    0.43
    rota
    0.43
    Activations Density 0.001%

    No Known Activations