© 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. 1944
    Prev
    Next
    INDEX
    Explanations

    window calculation configuration

    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
    мани
    2.65
    𝙩
    2.59
    𝘁
    2.54
    𝙧
    2.51
    Quel
    2.45
    𝙞
    2.42
    𝙚
    2.42
     ModelAndView
    2.34
    webdriver
    2.34
    म
    2.34
    POSITIVE LOGITS
     カット
    1.99
    oing
    1.90
    o
    1.89
     ويكيپيديا
    1.84
    alda
    1.82
    olet
    1.82
    े
    1.79
    caya
    1.77
    orescence
    1.76
    berly
    1.76
    Activations Density 0.040%

    No Known Activations