© 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. 84319
    Prev
    Next
    INDEX
    Explanations

    numbers and ordering

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

    importance and context

    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
    sendStatus
    0.49
    кг
    0.47
    Һ
    0.46
    न्स
    0.44
    多く
    0.44
    듭
    0.43
    ;_
    0.43
     ভাষায়
    0.42
    Χ
    0.42
     вули
    0.42
    POSITIVE LOGITS
     unfore
    0.50
     Ebola
    0.50
    estre
    0.49
     Second
    0.48
     paramedic
    0.46
     ორი
    0.46
     Allison
    0.45
     segunda
    0.45
     Segunda
    0.45
     two
    0.44
    Activations Density 0.006%

    No Known Activations