© 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. 122468
    Prev
    Next
    INDEX
    Explanations

    geo-coordinates and directions

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

    coordinates with N or S

    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
    㗆
    0.42
    옳
    0.42
    资源
    0.41
    决策
    0.41
    FUL
    0.40
     इनकी
    0.40
    鬪
    0.40
    Prosec
    0.39
    asign
    0.39
    toothbrush
    0.39
    POSITIVE LOGITS
     euros
    0.43
     www
    0.43
     Levante
    0.42
     supplemented
    0.42
    cas
    0.40
    バン
    0.40
     αυ
    0.40
     gep
    0.39
     Gipps
    0.39
    ≙
    0.39
    Activations Density 0.000%

    No Known Activations