© 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. 4366
    Prev
    Next
    INDEX
    Explanations

    function returns

    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
    5
    0.93
    7
    0.89
    1
    0.87
    3
    0.86
    8
    0.84
    a
    0.80
     Во
    0.80
    mobile
    0.77
     вод
    0.77
     அதில்
    0.76
    POSITIVE LOGITS
    Bechyné
    1.56
    <unused257>
    1.44
    <unused527>
    1.44
    <unused578>
    1.44
     shouldUse
    1.43
    <unused293>
    1.40
    <unused284>
    1.39
    <unused1940>
    1.39
     সহজাত
    1.38
     SUSY
    1.38
    Activations Density 0.028%

    No Known Activations