© 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. 225517
    Prev
    Next
    INDEX
    Explanations

    airports in, Homes in

    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
    的
    0.53
    veck
    0.46
     deshalb
    0.46
    fehler
    0.45
     ansch
    0.45
    別
    0.45
    ༞
    0.45
    でしょう
    0.45
    くん
    0.44
    耀
    0.44
    POSITIVE LOGITS
     )
    0.45
     Pue
    0.45
     اصلی
    0.45
     కూ
    0.45
     amiable
    0.44
    indication
    0.44
     کس
    0.44
     пары
    0.43
     indication
    0.43
     زاده
    0.42
    Activations Density 0.002%

    No Known Activations