Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 3134
    Prev
    Next
    INDEX
    Explanations

    especially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ,
    1.40
    :
    1.06
    (?)
    0.92
    ,...
    0.92
    ,?
    0.89
    的是
    0.88
    ,\\
    0.86
    ...
    0.86
    :
    0.86
    ,..
    0.84
    POSITIVE LOGITS
     причем
    1.86
     což
    1.82
     takže
    1.80
     sodass
    1.79
     которая
    1.73
    从而
    1.71
     което
    1.69
     тобто
    1.69
    并且
    1.67
     которое
    1.67
    Activations Density 0.026%

    No Known Activations