© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84541
    Prev
    Next
    INDEX
    Explanations

    code/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    の準備
    -1.77
    に入れ
    -1.75
    が可能
    -1.74
     politiche
    -1.66
    をお願い
    -1.59
    んでしょう
    -1.53
    を行い
    -1.49
     femmin
    -1.49
    に入れる
    -1.48
    Vlastnosti
    -1.48
    POSITIVE LOGITS
    を
    1.87
    などが
    1.71
    などを
    1.58
    なども
    1.41
    '
    1.37
     generalmente
    1.36
    つまり
    1.33
     trusty
    1.30
    ;
    1.26
    特别是
    1.25
    Activations Density 0.084%

    No Known Activations