© 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. 164298
    Prev
    Next
    INDEX
    Explanations

    forthwith, promptly, miraculously, corroborated

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

    beginning or immediate actions

    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
    pok
    0.45
    டத்தில்
    0.44
     쉽
    0.43
    pes
    0.42
     बोतल
    0.42
     Телефон
    0.41
     தோல்
    0.41
    ？
    0.41
     gimm
    0.40
    conex
    0.40
    POSITIVE LOGITS
    زمت
    0.49
     forthwith
    0.49
     miraculously
    0.48
     corroborate
    0.47
    新たに
    0.46
     constater
    0.45
     brainchild
    0.45
     promptly
    0.44
    بري
    0.43
     rallied
    0.43
    Activations Density 0.001%

    No Known Activations