© 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. 136330
    Prev
    Next
    INDEX
    Explanations

    software and service names

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

    dandelion clocks

    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
    爯
    0.60
     刘
    0.51
    Durch
    0.48
    arono
    0.46
    сім
    0.46
     потребуется
    0.45
    芰
    0.44
    䔧
    0.44
     різних
    0.43
    㕧
    0.43
    POSITIVE LOGITS
     hotline
    0.48
     campuses
    0.46
     confidentiality
    0.45
     vacancies
    0.44
    澀
    0.44
     athletes
    0.43
     days
    0.43
     delinquency
    0.43
     day
    0.42
     educativa
    0.42
    Activations Density 0.002%

    No Known Activations