© 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. 30899
    Prev
    Next
    INDEX
    Explanations

    Canadian postal codes

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

    numbers and codes

    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
    typeparam
    0.40
    rea
    0.37
     Siddh
    0.35
    ifrån
    0.35
    sourceEncoding
    0.34
    Ꮘ
    0.33
     Lith
    0.33
    ટા
    0.33
    uptools
    0.33
     suivante
    0.33
    POSITIVE LOGITS
    萱
    0.44
     Второй
    0.41
     saliva
    0.40
     tinge
    0.39
     âm
    0.39
    TING
    0.38
     首
    0.38
     रक्त
    0.38
     milky
    0.38
     rive
    0.38
    Activations Density 0.071%

    No Known Activations