© 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. 219515
    Prev
    Next
    INDEX
    Explanations

    general language processing

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

    movie, camera, GB, New York, banker

    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
    נט
    0.45
    מא
    0.45
    ズ
    0.45
     perched
    0.44
    ラ
    0.44
    MICRO
    0.43
    華
    0.43
    成長
    0.42
    PRINC
    0.42
    원
    0.42
    POSITIVE LOGITS
     အတွ
    0.50
     नूर
    0.48
    icam
    0.47
    TabBar
    0.46
     මෙය
    0.46
     договора
    0.46
     акты
    0.46
     थरूर
    0.45
    了这个
    0.45
     tartal
    0.44
    Activations Density 0.001%

    No Known Activations