© 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. 180773
    Prev
    Next
    INDEX
    Explanations

    geographical entities

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

    activity layouts

    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
     gode
    0.51
    E
    0.50
    G
    0.49
     sunt
    0.48
    Gal
    0.48
    Gly
    0.48
     চীনা
    0.48
    Exerc
    0.48
    Galer
    0.48
    Nombre
    0.46
    POSITIVE LOGITS
    ণ
    0.49
    前景
    0.45
    他也
    0.44
    浯
    0.42
    rists
    0.42
    似的
    0.42
     LINKS
    0.41
     వలన
    0.41
    genden
    0.40
    深深
    0.40
    Activations Density 0.000%

    No Known Activations