© 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-65K
    7. 13351
    Prev
    Next
    INDEX
    Explanations

    without

    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_65k_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
    爀
    0.40
    elsior
    0.39
    ̽
    0.38
    myCollision
    0.38
     болу
    0.37
     moderately
    0.37
    ඇ
    0.36
    龊
    0.35
     mediocre
    0.35
    જબ
    0.35
    POSITIVE LOGITS
     without
    1.82
     tanpa
    1.74
     बिना
    1.66
     ohne
    1.66
    without
    1.66
     zonder
    1.66
     بدون
    1.65
     без
    1.61
     Without
    1.59
     WITHOUT
    1.59
    Activations Density 0.858%

    No Known Activations