© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81197
    Prev
    Next
    INDEX
    Explanations

    "between periods" or "right for"

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )-
    0.50
    довле
    0.43
    )-\
    0.43
    に関しては
    0.42
     করিয়া
    0.42
     prawn
    0.41
    apk
    0.41
    તિ
    0.41
    ক
    0.40
    ）
    0.40
    POSITIVE LOGITS
     رياضيات
    0.50
    యత్
    0.44
    يرين
    0.44
     mathematicians
    0.42
    ناط
    0.42
    ቈ
    0.41
    studentid
    0.39
    studentRecord
    0.39
    㷅
    0.39
     নির্ধারণ
    0.38
    Activations Density 0.002%

    No Known Activations