© 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. 237700
    Prev
    Next
    INDEX
    Explanations

    emerging markets, printing, huge library, answered, opposed, set

    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
     {};
    0.46
    haven
    0.43
    ordes
    0.42
    inec
    0.42
    Y
    0.42
    ount
    0.42
     duc
    0.41
    away
    0.41
    ord
    0.41
    busters
    0.40
    POSITIVE LOGITS
    ᒫ
    0.50
    横浜
    0.49
    ни
    0.48
    ре
    0.48
    િવસે
    0.48
    ்தான்
    0.47
     Unternehmens
    0.46
    ர
    0.46
    鼹
    0.46
     этом
    0.46
    Activations Density 0.000%

    No Known Activations