© 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. 80278
    Prev
    Next
    INDEX
    Explanations

    asking and inquiring

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

    Islamic historical 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
     sensibly
    0.52
    াহিনীর
    0.52
     deliverance
    0.52
     veuillez
    0.51
    ப்பர்
    0.51
    訸
    0.51
     progressing
    0.50
    र्सन
    0.48
     scripture
    0.48
     necessitating
    0.47
    POSITIVE LOGITS
     बताएं
    0.49
     مسجد
    0.47
     لوگوں
    0.46
     ع
    0.46
     ót
    0.46
     ônibus
    0.45
    告诉我
    0.45
     thí
    0.44
     관리
    0.44
     লোকদের
    0.44
    Activations Density 0.040%

    No Known Activations