© 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. 4774
    Prev
    Next
    INDEX
    Explanations

    "or should I walk by again?"

    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
    t
    1.66
    s
    1.54
    even
    1.47
    e
    1.46
    timer
    1.44
     đâu
    1.42
    tin
    1.42
    tie
    1.42
    '
    1.41
    ty
    1.40
    POSITIVE LOGITS
     zahlreiche
    2.14
     birçok
    2.09
     outras
    2.04
     innych
    2.04
     iba
    2.03
     कई
    2.03
     viele
    2.02
     otras
    2.00
     weiterer
    1.97
     wenige
    1.97
    Activations Density 0.142%

    No Known Activations