© 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. 31-GEMMASCOPE-2-RES-262K
    7. 71371
    Prev
    Next
    INDEX
    Explanations

    Compatibility

    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
     Decimal
    0.42
     ฝึก
    0.40
    </td>
    0.40
    abel
    0.39
     Model
    0.39
     involves
    0.39
     do
    0.38
    Adopt
    0.38
    ci
    0.38
    Cell
    0.38
    POSITIVE LOGITS
    ヤマ
    0.46
     مها
    0.45
     ప్రజా
    0.43
     antiga
    0.43
    萫
    0.42
     maxime
    0.42
    やま
    0.41
    ರಿನ
    0.41
    調
    0.41
     measurements
    0.40
    Activations Density 0.004%

    No Known Activations