© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133755
    Prev
    Next
    INDEX
    Explanations

    common phrases and collocations

    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_40_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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.48
    qid
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
    Segments
    0.41
    Logged
    0.41
     แปร
    0.40
    StartY
    0.40
     CWE
    0.40
     Еўропы
    0.40
     клет
    0.40
    POSITIVE LOGITS
     اصلي
    0.39
     কাজল
    0.38
     voices
    0.36
     bson
    0.36
    颛
    0.36
     dogma
    0.36
     color
    0.35
    形状
    0.35
     speaking
    0.35
     passive
    0.35
    Activations Density 0.000%

    No Known Activations