© 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. 107595
    Prev
    Next
    INDEX
    Explanations

    manifest definition, manifesto, installer, hierarchy

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

    manifesto or manifest

    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
     огромное
    0.59
     большое
    0.56
    z
    0.55
    mé
    0.50
     величе
    0.47
     сцене
    0.47
    kz
    0.47
    atthena
    0.46
     лёг
    0.46
     Negative
    0.46
    POSITIVE LOGITS
     innovate
    0.51
     learn
    0.49
     measure
    0.47
    學習
    0.46
     passo
    0.45
     신
    0.43
    ോട്ടോ
    0.43
     desse
    0.43
     scaffold
    0.43
    าวิ
    0.42
    Activations Density 0.000%

    No Known Activations