© 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. 28305
    Prev
    Next
    INDEX
    Explanations

    state management

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

    ">

    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
    lt
    0.44
    笂
    0.40
     لت
    0.40
     redis
    0.40
    Boy
    0.40
     anunci
    0.39
    getSelected
    0.39
     τησ
    0.39
     탁
    0.38
     televiz
    0.38
    POSITIVE LOGITS
    IDENCE
    0.46
     legality
    0.43
    丈
    0.43
    ADEM
    0.42
     ভিত্তি
    0.41
     spelt
    0.41
     axles
    0.41
    ytical
    0.41
    IEF
    0.40
    䅐
    0.40
    Activations Density 0.000%

    No Known Activations