© 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. 41585
    Prev
    Next
    INDEX
    Explanations

    predicting noun phrases often following 'a' or 'from'

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

    common sentence structures

    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
     scathing
    0.49
    산
    0.45
    whatever
    0.44
    만이
    0.43
     mans
    0.42
    w
    0.42
    asts
    0.42
     mechan
    0.42
     hùng
    0.42
     that
    0.40
    POSITIVE LOGITS
    疫情
    0.47
    墘
    0.47
     πριν
    0.47
    常見
    0.47
    导致
    0.46
     เซ
    0.46
     způso
    0.46
    畲
    0.46
     مختلفة
    0.46
     ہماری
    0.46
    Activations Density 0.000%

    No Known Activations