© 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. 149858
    Prev
    Next
    INDEX
    Explanations

    words followed by the

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

    detailing, depicting, portraying harm

    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
    íonn
    0.45
     conserva
    0.42
     począ
    0.42
     washington
    0.41
     Cary
    0.41
    .";
    0.41
    িয়াছে
    0.41
     auctions
    0.40
    活动的
    0.40
    POSITIVE LOGITS
     fantastical
    0.50
     ठीक
    0.48
     आश्चर्य
    0.47
     Конститу
    0.46
     മികച്ച
    0.45
     Shree
    0.45
    გილ
    0.44
     シルバー
    0.44
     титу
    0.44
    ▄
    0.44
    Activations Density 0.005%

    No Known Activations