© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 46457
    Prev
    Next
    INDEX
    Explanations

    script interpreters via env

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.73
     WordPerfect
    0.55
     Appro
    0.53
     AppPage
    0.52
     Wittgenstein
    0.52
     Precambrian
    0.52
    悹
    0.51
    Appro
    0.50
     App
    0.48
     Krom
    0.48
    POSITIVE LOGITS
    و
    0.69
    ка
    0.59
    ﻭ
    0.54
    ᄐ
    0.53
     perjalanan
    0.52
     наличии
    0.51
     contesto
    0.49
     caramelized
    0.49
     전쟁
    0.49
    ар
    0.49
    Activations Density 0.000%

    No Known Activations