© 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. 69510
    Prev
    Next
    INDEX
    Explanations

    you, me, my, him

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

    maintaining integrity and commitment

    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
     KEYUP
    0.55
     LUX
    0.48
    natal
    0.47
     ដ
    0.45
     harmonica
    0.43
    ų
    0.43
     Hương
    0.43
    ヒット
    0.43
    unpriv
    0.43
    うる
    0.42
    POSITIVE LOGITS
    伈
    0.49
    Subsection
    0.49
     Syed
    0.48
    Sz
    0.47
     অধিনায়ক
    0.46
     Examiner
    0.46
     contrario
    0.46
    кса
    0.45
    Giovanni
    0.45
    cis
    0.44
    Activations Density 0.001%

    No Known Activations