© 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. 67109
    Prev
    Next
    INDEX
    Explanations

    Cambodian Saturday morning portions

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

    respect or skilled migrant visa

    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
    獒
    0.45
     দৈনিক
    0.44
    사이트
    0.44
     adicional
    0.43
     बल्ब
    0.42
     विंडो
    0.42
    뻘
    0.42
    底下
    0.42
     koristiti
    0.41
    βολ
    0.41
    POSITIVE LOGITS
    '
    0.52
     Riding
    0.51
    getClass
    0.45
    represented
    0.45
    they
    0.45
    aphys
    0.44
     représentent
    0.44
     envers
    0.44
    law
    0.44
     représente
    0.44
    Activations Density 0.000%

    No Known Activations