© 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. 2223
    Prev
    Next
    INDEX
    Explanations

    placeholders for names and identifiers

    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
    וֹ
    1.87
    всем
    1.84
    撗
    1.69
     \|\
    1.68
    =","><
    1.67
     वाइज
    1.66
     דער
    1.65
     pInBuffer
    1.65
     चैंप
    1.63
    оп
    1.63
    POSITIVE LOGITS
     in
    1.64
     and
    1.59
     serves
    1.58
     provides
    1.55
     has
    1.51
     offers
    1.50
     is
    1.42
     lacks
    1.39
    '
    1.37
     makes
    1.33
    Activations Density 0.188%

    No Known Activations