© 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. 152145
    Prev
    Next
    INDEX
    Explanations

    video quality, born in, minimum write speeds

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

    automotive sector

    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
    ovaný
    0.48
     nft
    0.46
     উৎপন্ন
    0.45
     both
    0.43
     nv
    0.43
     carer
    0.43
    媧
    0.42
    েশন
    0.42
     zowel
    0.42
     Nt
    0.42
    POSITIVE LOGITS
    Ack
    0.45
     восто
    0.43
     Петер
    0.43
    ныгы
    0.42
     acknowled
    0.41
    Ар
    0.41
    Ტ
    0.41
     문제가
    0.40
     высокой
    0.40
    .\\
    0.39
    Activations Density 0.000%

    No Known Activations