© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68065
    Prev
    Next
    INDEX
    Explanations

    the word now

    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
    3
    -3.06
    0
    -3.00
    2
    -2.80
    1
    -2.52
    6
    -2.44
    あー
    -2.31
    </h3>
    -2.30
     mangel
    -2.27
    7
    -2.19
    </strong>
    -2.17
    POSITIVE LOGITS
    ！！”
    2.98
    鹇
    2.97
    褔
    2.92
    镦
    2.83
    =\""
    2.63
    泺
    2.58
    梣
    2.58
    涠
    2.53
    atasaray
    2.47
    孭
    2.47
    Activations Density 0.049%

    No Known Activations