© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3627
    Prev
    Next
    INDEX
    Explanations

    words inside quotes or parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ⟋
    2.46
    “
    2.42
     “[
    2.41
    ,$$
    2.40
     __________
    2.40
    ăș
    2.39
    ționale
    2.39
    —“
    2.37
     _____________
    2.35
     “
    2.35
    POSITIVE LOGITS
    ,’
    3.71
    .’
    3.62
    ,'
    3.51
    ’,
    3.39
    .'
    3.31
    ',
    3.31
    ’.
    3.18
    !’
    3.18
    !'
    3.13
    ','
    3.09
    Activations Density 0.251%

    No Known Activations