© 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. 31398
    Prev
    Next
    INDEX
    Explanations

    business operations

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

    geographical and conceptual relationships

    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
    ইহার
    0.52
    獷
    0.51
    ”،
    0.49
     xhrObj
    0.49
    挑戰
    0.48
    ”、“
    0.46
     tumeurs
    0.46
    、$
    0.46
    格納
    0.45
     τέ
    0.45
    POSITIVE LOGITS
    PTV
    0.51
     Ples
    0.50
     PT
    0.49
     Buk
    0.49
     Pact
    0.49
     Masa
    0.49
    0.49
     Jul
    0.48
     Mi
    0.48
     McCl
    0.48
    Activations Density 0.000%

    No Known Activations