© 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. 172426
    Prev
    Next
    INDEX
    Explanations

    drug prevention provider

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

    descriptive text sections

    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
     sechs
    0.51
     ચૂક
    0.51
     আকার
    0.48
     முருக
    0.47
     हृदया
    0.47
    கடந்த
    0.47
     Başkan
    0.46
    摶
    0.45
     निश्च
    0.45
    гур
    0.45
    POSITIVE LOGITS
    )
    0.52
    )~
    0.47
     )
    0.45
    sdag
    0.45
    stad
    0.44
    ）
    0.44
    stit
    0.43
     بهم
    0.43
     promenade
    0.43
    stav
    0.43
    Activations Density 0.001%

    No Known Activations