© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 824
    Prev
    Next
    INDEX
    Explanations

    verbs followed by articles or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite

    start typing, suggest ideas, built into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    õe
    0.41
     nonfiction
    0.38
    .\"
    0.37
     betrachtet
    0.36
     setzt
    0.35
     kaleidoscopic
    0.35
     égard
    0.35
    🙌
    0.34
    間の
    0.33
     dotyczą
    0.33
    POSITIVE LOGITS
    /
    0.36
    Z
    0.35
    and
    0.34
     Bertha
    0.33
     (!)
    0.33
    Jenny
    0.33
     Lizzy
    0.32
     предвари
    0.32
     FOM
    0.32
     Lucia
    0.32
    Activations Density 0.395%

    No Known Activations