© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81197
    Prev
    Next
    INDEX
    Explanations

    processing and calculation

    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
    )-
    0.54
    )-\
    0.47
    તિ
    0.46
    )
    0.46
    ))
    0.43
    ক
    0.42
    นาน
    0.41
    )+(
    0.40
    }}+\
    0.40
    agamanam
    0.40
    POSITIVE LOGITS
    يرين
    0.44
     رياضيات
    0.43
    ቈ
    0.43
    ناط
    0.41
    㷅
    0.41
     ethnicities
    0.40
     შემთხვევ
    0.40
    私募基金管理人
    0.39
     mathematicians
    0.39
    éro
    0.39
    Activations Density 0.003%

    No Known Activations