© 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. 20035
    Prev
    Next
    INDEX
    Explanations

    justify-content: space-between

    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
    ጇ
    0.55
     издание
    0.55
     механи
    0.54
     setor
    0.54
     мати
    0.53
    0
    0.53
     tenha
    0.52
     সড়
    0.52
    晾
    0.52
     zdravot
    0.51
    POSITIVE LOGITS
    s
    0.75
    の部分
    0.59
    purs
    0.56
    -
    0.53
    silyl
    0.53
    প
    0.51
    ات
    0.50
    ের
    0.50
    にとって
    0.50
    su
    0.49
    Activations Density 0.000%

    No Known Activations