© 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. 2564
    Prev
    Next
    INDEX
    Explanations

    versioning and iteration

    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
    ளுடைய
    1.86
    /=
    1.83
    ൂപ
    1.79
    ുതി
    1.77
     착
    1.76
    ಗಳನ್ನು
    1.75
    setDescription
    1.75
     MODIFY
    1.75
    CHREIB
    1.72
    DebuggingMode
    1.72
    POSITIVE LOGITS
    a
    1.33
    b
    1.33
     and
    1.33
    enso
    1.31
    iros
    1.30
    ev
    1.29
    er
    1.28
    obacteria
    1.27
    ubern
    1.26
    rica
    1.26
    Activations Density 0.212%

    No Known Activations