© 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. 241161
    Prev
    Next
    INDEX
    Explanations

    also, statements and notice

    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
    ンス
    0.48
    只限
    0.46
    RELATIVA
    0.46
     сега
    0.43
     FROM
    0.42
    יל
    0.40
    raient
    0.40
    為
    0.40
     शुरु
    0.39
    浪
    0.39
    POSITIVE LOGITS
     również
    0.59
     también
    0.55
     także
    0.54
     myös
    0.54
     আবারও
    0.51
     देखील
    0.49
     også
    0.49
     أيضًا
    0.48
     içerisinde
    0.48
     également
    0.47
    Activations Density 0.001%

    No Known Activations