© 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. 139553
    Prev
    Next
    INDEX
    Explanations

    searching for new ideas

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

    grammatically correct usage

    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
    ̷
    0.47
     troughs
    0.45
    <0xB3>
    0.45
     đêm
    0.44
     น่า
    0.44
     proclaimed
    0.43
     хуже
    0.43
     αι
    0.43
     ၂
    0.42
    contro
    0.42
    POSITIVE LOGITS
    자
    0.51
    ंजन
    0.49
     alltid
    0.46
    offic
    0.46
    ण
    0.45
    innah
    0.44
    ן
    0.44
    相手
    0.43
     estilos
    0.43
    hende
    0.42
    Activations Density 0.001%

    No Known Activations