© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202372
    Prev
    Next
    INDEX
    Explanations

    each half

    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_31_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
     Сколько
    0.53
     Исто
    0.51
     zobraz
    0.49
     उदाहरण
    0.49
    內
    0.47
     ፍ
    0.46
     отобра
    0.46
    čně
    0.45
     расходы
    0.45
    ប្រតិ
    0.45
    POSITIVE LOGITS
     certes
    0.43
    Adjacent
    0.43
     MgII
    0.43
    ँची
    0.42
    噪音
    0.41
    WAM
    0.40
    仔
    0.40
    adina
    0.39
    Definitely
    0.39
    льним
    0.39
    Activations Density 0.000%

    No Known Activations