© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3531
    Prev
    Next
    INDEX
    Explanations

    I following punctuation

    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_12_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
    ások
    2.55
    ással
    2.39
    )^{[\
    2.33
    ásra
    2.29
    <unused1033>
    2.28
    ꗧ
    2.26
    ása
    2.25
     주목
    2.24
    𒑉
    2.24
    áver
    2.23
    POSITIVE LOGITS
     I
    3.66
    I
    3.34
     my
    2.47
     myself
    2.28
     me
    2.26
    我
    2.24
    my
    2.24
     saya
    2.22
    我已经
    2.02
    我很
    2.02
    Activations Density 0.752%

    No Known Activations