© 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. 67823
    Prev
    Next
    INDEX
    Explanations

    worth doing

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

    repeat if

    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
     CLIENTI
    0.59
    客户端
    0.52
    iemi
    0.52
     पाकिस्तानी
    0.50
    用
    0.50
    ですか
    0.49
    ਾਰੇ
    0.49
    כ
    0.48
    手機
    0.48
    ך
    0.47
    POSITIVE LOGITS
    ething
    0.45
     Gelegenheit
    0.44
     keenly
    0.44
     prolonged
    0.44
     grouse
    0.44
     flamboyant
    0.43
     something
    0.43
     generation
    0.43
     historic
    0.43
     superbly
    0.42
    Activations Density 0.000%

    No Known Activations