© 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. 69079
    Prev
    Next
    INDEX
    Explanations

    variety of things

    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
    ⎚
    -2.77
    踽
    -2.56
     devising
    -2.55
     serán
    -2.48
     wth
    -2.38
    廰
    -2.36
     stalwart
    -2.33
    ᗷ
    -2.33
     devast
    -2.28
     wichtigste
    -2.28
    POSITIVE LOGITS
     of
    2.56
    𖡼
    2.52
    芣
    2.44
    0
    2.41
    .
    2.33
     increase
    2.16
    〜。
    2.13
     ihre
    2.13
     и
    2.09
     krä
    2.08
    Activations Density 0.022%

    No Known Activations