© 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. 102761
    Prev
    Next
    INDEX
    Explanations

    phrases following common words

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

    risk level

    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
    这件事
    0.47
    ευ
    0.43
    י
    0.42
     conv
    0.41
    铺
    0.41
    这场
    0.41
     OF
    0.41
     Developers
    0.41
     transaction
    0.40
    ukasz
    0.40
    POSITIVE LOGITS
    )".
    0.52
     racionais
    0.51
    )”.
    0.50
    governmental
    0.48
     appointees
    0.46
     கிட்ட
    0.45
     казіно
    0.45
    Angles
    0.44
    鰓
    0.44
     màn
    0.44
    Activations Density 0.001%

    No Known Activations