© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2549
    Prev
    Next
    INDEX
    Explanations

    considering different languages

    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
    ,»
    2.24
    »:
    2.19
    !»
    2.18
    »
    2.13
    .»
    2.00
    »,
    1.90
    «,
    1.87
     »
    1.86
    «.
    1.83
    ?»
    1.81
    POSITIVE LOGITS
    <0x0D>
    2.27
    ieszcz
    1.15
    ingleton
    1.06
     szcz
    0.99
    хову
    0.99
    ธิ
    0.96
     """
    0.94
    ักษ
    0.92
    祓
    0.90
     ugljik
    0.90
    Activations Density 0.001%

    No Known Activations