© 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. 106408
    Prev
    Next
    INDEX
    Explanations

    unified brand

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

    key, shows self, width can, major annoyance, valuable examples, CSV file

    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
    રણ
    0.49
    ření
    0.48
    녕하
    0.47
    尔
    0.47
    𝘄
    0.46
     갖
    0.45
    必备
    0.45
    ሚ
    0.45
    ılar
    0.45
    ார்க
    0.45
    POSITIVE LOGITS
     diva
    0.49
     decline
    0.47
     hugely
    0.44
     WhatsApp
    0.43
    <b>
    0.42
     node
    0.42
     shrou
    0.42
    ذه
    0.41
     manuscript
    0.41
     cep
    0.41
    Activations Density 0.001%

    No Known Activations