© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109598
    Prev
    Next
    INDEX
    Explanations

    prompts requesting, someone looking, psychedelics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    iological
    0.46
    i
    0.46
    وا
    0.45
     grammar
    0.42
     یا
    0.42
    initializer
    0.42
    入り
    0.42
    your
    0.42
    ⑸
    0.41
     fina
    0.40
    POSITIVE LOGITS
     архив
    0.44
     Digests
    0.44
    :
    0.44
     จำ
    0.44
    :\
    0.44
    :</
    0.43
    nahmen
    0.43
    даги
    0.43
     posits
    0.42
    谧
    0.42
    Activations Density 0.008%

    No Known Activations