© 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. 166300
    Prev
    Next
    INDEX
    Explanations

    necessary special permits

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

    within or alternating

    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
    এইচ
    0.55
     এইচ
    0.52
     Análisis
    0.50
     reconocimiento
    0.48
    ިޔ
    0.48
     Анали
    0.48
    Ν
    0.48
     Ν
    0.47
     নল
    0.46
    N
    0.46
    POSITIVE LOGITS
     gates
    0.47
     cables
    0.46
     szpital
    0.45
    pherds
    0.45
     थिएटर
    0.44
     Carpath
    0.44
     batalha
    0.43
     tribes
    0.43
     ascension
    0.43
     wios
    0.43
    Activations Density 0.001%

    No Known Activations