© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1095
    Prev
    Next
    INDEX
    Explanations

    a or an

    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
     J
    1.18
     H
    1.16
    hmad
    1.11
     P
    1.07
    uda
    1.07
    rizona
    1.07
    uba
    1.07
    J
    1.05
    eg
    1.04
     Ma
    1.04
    POSITIVE LOGITS
     veditabbo
    1.59
    るので
    1.57
    <unused1237>
    1.57
     imassa
    1.52
     хотя
    1.52
     tasmim
    1.52
     complementar
    1.51
     nirvach
    1.49
     asymmetries
    1.48
    <unused1252>
    1.46
    Activations Density 0.762%

    No Known Activations