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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10861
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or verbs

    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_10/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
    靫
    -2.23
    𓆜
    -2.14
    )."
    -2.11
    ')
    -2.08
     kemajuan
    -1.98
    鈇
    -1.97
    恫
    -1.93
    ㅈ
    -1.88
    ⌄
    -1.88
    傕
    -1.84
    POSITIVE LOGITS
    *
    2.59
    “
    2.44
    <i>
    2.44
    It
    2.13
    ’
    2.09
     However
    2.00
    from
    1.96
    there
    1.95
    足以
    1.91
    ederos
    1.89
    Activations Density 0.001%

    No Known Activations