© 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. 23497
    Prev
    Next
    INDEX
    Explanations

    revealing despicable professions

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

    exploited by codebreakers

    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
     Lydia
    0.52
     Minister
    0.50
     Kluwer
    0.48
    ا
    0.46
    枻
    0.44
     Jeopardy
    0.44
     Mano
    0.44
     Kathleen
    0.43
     navigational
    0.43
    烜
    0.43
    POSITIVE LOGITS
    vitro
    0.55
    wast
    0.51
     moulds
    0.50
    vf
    0.50
    myTransform
    0.49
    mlst
    0.48
    moire
    0.47
    šky
    0.47
    lafen
    0.47
    mobilpay
    0.47
    Activations Density 0.000%

    No Known Activations