© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

    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
    2
    1.46
    atic
    1.43
    erm
    1.42
    urn
    1.38
    ом
    1.32
    of
    1.28
    resher
    1.28
    llr
    1.23
     wreck
    1.23
    3
    1.22
    POSITIVE LOGITS
     özellikle
    1.76
     sangat
    1.70
    િલે
    1.70
     zcela
    1.67
     EditorGUILayout
    1.67
     berbagai
    1.66
     kapasitas
    1.66
     úpl
    1.65
     kesin
    1.64
     teknologi
    1.63
    Activations Density 0.022%

    No Known Activations