© 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. 251903
    Prev
    Next
    INDEX
    Explanations

    business contexts, achievements, or roles

    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
     Takeuchi
    0.51
    CloseOperation
    0.49
    자기
    0.49
    Converting
    0.48
     Converts
    0.48
    ௐ
    0.47
     श्रीमती
    0.46
    睛
    0.45
    მასრულ
    0.44
    atil
    0.44
    POSITIVE LOGITS
    ille
    0.47
    エル
    0.47
    j
    0.45
    se
    0.45
     brood
    0.44
     critic
    0.44
     compat
    0.44
     on
    0.44
     conduit
    0.44
    xia
    0.43
    Activations Density 0.000%

    No Known Activations