© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12511
    Prev
    Next
    INDEX
    Explanations

    the word classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ھر
    2.47
    ürü
    2.44
    weite
    2.31
    weiten
    2.28
    του
    2.23
     tanıt
    2.19
    يات
    2.10
     "{{
    2.08
    ۪
    2.08
    bral
    2.08
    POSITIVE LOGITS
     involuntarily
    2.72
    ו
    2.64
    槤
    2.59
    нков
    2.48
    UTONIUM
    2.48
     defaulted
    2.47
    心中的
    2.44
    ಿರಿ
    2.44
    spersed
    2.40
     distinguishing
    2.39
    Activations Density 0.016%

    No Known Activations