© 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. 211259
    Prev
    Next
    INDEX
    Explanations

    serving customers globally

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

    URL, workers, gnome, Karl, chance

    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
     що
    0.53
    </h5>
    0.49
     取
    0.49
     ख़
    0.47
     zweiten
    0.47
     கொடு
    0.46
    دى
    0.45
     通常
    0.44
    媒介
    0.44
    тування
    0.44
    POSITIVE LOGITS
    病情
    0.52
    鄴
    0.48
     Plantation
    0.47
    enaire
    0.45
    projectName
    0.44
    elder
    0.43
    maire
    0.43
    g
    0.43
     oor
    0.43
    name
    0.42
    Activations Density 0.000%

    No Known Activations