© 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. 190098
    Prev
    Next
    INDEX
    Explanations

    has a child

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

    learn to predict

    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
     لهم
    0.49
     وعلى
    0.47
    ="#!"
    0.47
     эффектив
    0.47
    職場
    0.46
     رو
    0.46
     форма
    0.46
     tật
    0.46
     svou
    0.45
     العالم
    0.44
    POSITIVE LOGITS
    E
    0.50
    petit
    0.48
    Chem
    0.47
    ポ
    0.47
    hank
    0.46
    スーパー
    0.45
    SP
    0.45
    Spar
    0.45
    birth
    0.44
    traverse
    0.44
    Activations Density 0.002%

    No Known Activations