© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211898
    Prev
    Next
    INDEX
    Explanations

    following common phrases

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

    overarching themes or user account

    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
    Negative Logits
     ከመ
    0.50
    コットン
    0.44
     among
    0.42
    hamming
    0.41
     {*}
    0.40
     بالأ
    0.40
     admissibility
    0.40
     আবি
    0.39
    among
    0.39
     तृ
    0.39
    POSITIVE LOGITS
    sonsten
    0.46
     noto
    0.46
     poca
    0.45
    اکر
    0.44
     scritt
    0.43
     presup
    0.43
    м
    0.43
     Tenants
    0.42
     ritual
    0.42
     concetto
    0.42
    Activations Density 0.000%

    No Known Activations