© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7014
    Prev
    Next
    INDEX
    Explanations

    self. attribute access

    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_13_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
    c
    1.55
    medi
    1.51
    ni
    1.44
    kst
    1.44
    cı
    1.41
    شده
    1.39
    cü
    1.31
    to
    1.27
     individual
    1.23
     Individual
    1.20
    POSITIVE LOGITS
    ធាតុ
    2.31
    ⠈
    2.19
    iotic
    2.13
    ພັນ
    2.07
    мпаваць
    2.07
    itespace
    2.06
     архив
    2.06
    ມາ
    2.05
     maxit
    2.05
    indungi
    2.04
    Activations Density 0.004%

    No Known Activations