© 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. 153003
    Prev
    Next
    INDEX
    Explanations

    available languages

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

    harmful or hurtful expressions

    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
    යෙන්
    0.46
    继续
    0.46
    벡터
    0.45
    пси
    0.45
     pog
    0.43
    大师
    0.43
    에
    0.42
    по
    0.42
    იდ
    0.41
    сю
    0.41
    POSITIVE LOGITS
    cuando
    0.49
     agricultural
    0.44
    AUTHENT
    0.44
    アニメ
    0.43
    emetery
    0.43
    ಕು
    0.43
    urbance
    0.43
     украин
    0.43
     کھانا
    0.43
    r
    0.42
    Activations Density 0.001%

    No Known Activations