© 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. 223134
    Prev
    Next
    INDEX
    Explanations

    related reference books

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

    even framed; a fun; on the

    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
     সম্বন্ধে
    0.46
    试图
    0.46
     census
    0.44
    尝试
    0.43
    сле
    0.42
    卻
    0.42
    户
    0.41
     attempting
    0.41
    驯
    0.41
     Trying
    0.41
    POSITIVE LOGITS
    ous
    0.47
    itario
    0.47
    oma
    0.47
     constamment
    0.46
     vorbere
    0.46
     blockchains
    0.46
     foolproof
    0.45
    Announcement
    0.45
     alimentaires
    0.44
     lucrat
    0.44
    Activations Density 0.000%

    No Known Activations