© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12933
    Prev
    Next
    INDEX
    Explanations

    actual identifier or path

    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
    ře
    2.16
    মধ্যে
    2.16
     dní
    2.07
    ese
    2.06
    ৃহে
    2.06
    elijke
    2.05
     gravy
    2.03
    ｬ
    2.03
    eln
    2.03
     bares
    2.02
    POSITIVE LOGITS
     copies
    1.89
    िटीज
    1.87
    하다고
    1.86
     Copies
    1.81
    ChildScrollView
    1.77
    AssemblyInfo
    1.74
    copies
    1.72
    keits
    1.70
    සු
    1.65
    IMENTS
    1.63
    Activations Density 0.082%

    No Known Activations