© 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. 5575
    Prev
    Next
    INDEX
    Explanations

    why do, file, goal, mutex, physical, crows

    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
    MiddleLine
    0.49
    र्फ
    0.47
     דר
    0.47
    splitLength
    0.47
    蓣
    0.46
    pathTemplates
    0.46
    pInBuffer
    0.46
     контро
    0.45
    ડા
    0.45
     possíveis
    0.45
    POSITIVE LOGITS
     your
    0.63
     by
    0.63
     to
    0.62
     you
    0.57
    ’
    0.51
     tele
    0.50
     file
    0.50
     guide
    0.50
     bios
    0.49
     one
    0.47
    Activations Density 0.000%

    No Known Activations