© 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. 184068
    Prev
    Next
    INDEX
    Explanations

    attracting visitors

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

    foundational reality of limited models

    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
    setzen
    0.62
    setzung
    0.60
    '}
    0.54
    ım
    0.52
    ın
    0.48
    `}
    0.48
     khoan
    0.48
    ün
    0.47
     zuletzt
    0.47
    '},
    0.46
    POSITIVE LOGITS
    क्क
    0.48
    0.47
    स्तिष्क
    0.45
    вае
    0.45
    Oe
    0.43
    డుగు
    0.43
    жени
    0.42
    йма
    0.42
    ब्स
    0.42
     ऋषि
    0.42
    Activations Density 0.000%

    No Known Activations