© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14746
    Prev
    Next
    INDEX
    Explanations

    control characters and separators

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

    hexadecimal strings

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

    Unicode formatting characters

    np_max-act · claude-4-5-sonnetTriggered by @sk5695

    Unicode spacing characters

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
     ಇನ್ನೂ
    0.47
    ively
    0.47
    izaciones
    0.44
    irnya
    0.43
    itabbo
    0.43
    bros
    0.41
    няя
    0.41
    ੀ
    0.41
     цве
    0.41
     ถาม
    0.41
    POSITIVE LOGITS
    OF
    0.58
    К
    0.54
    AS
    0.53
    ِلِّ
    0.52
    _
    0.52
     mít
    0.48
    由
    0.48
    ES
    0.47
    AN
    0.46
     lidí
    0.45
    Activations Density 0.045%

    No Known Activations