© 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. 3256
    Prev
    Next
    INDEX
    Explanations

    geographical names and institutions

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

    Office (x 5clear 5)Google BImarine Motor

    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
    힙
    0.37
     노
    0.36
     eminently
    0.36
    ｔ
    0.35
     పని
    0.35
    घन
    0.35
     исследова
    0.34
     कामगिरी
    0.34
    ৩৩
    0.34
    鲵
    0.33
    POSITIVE LOGITS
     with
    0.50
     during
    0.45
    ;
    0.43
    /
    0.43
    –
    0.43
     using
    0.39
     avec
    0.39
     including
    0.39
    with
    0.39
     without
    0.38
    Activations Density 0.235%

    No Known Activations