© 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. 145131
    Prev
    Next
    INDEX
    Explanations

    section of or board of

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

    variety of, released, once each

    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
    Архі
    0.48
    ској
    0.48
    드
    0.47
    RENT
    0.47
    фор
    0.46
    বর্ণ
    0.46
    йної
    0.45
    禮
    0.45
    Appellant
    0.45
    Ain
    0.43
    POSITIVE LOGITS
    zij
    0.45
     liberating
    0.44
    ops
    0.44
     tomat
    0.44
    ilat
    0.43
     successively
    0.43
     soya
    0.42
     sugarcane
    0.42
     lovable
    0.42
     polling
    0.41
    Activations Density 0.001%

    No Known Activations