© 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. 10-GEMMASCOPE-RES-131K
    7. 42797
    Prev
    Next
    INDEX
    Explanations

    fire followed by specific names

    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
    \
    -3.88
    ’
    -3.38
    O
    -3.08
    s
    -3.06
     
    -3.03
    "
    -3.03
    as
    -2.97
    U
    -2.92
    N
    -2.83
    E
    -2.81
    POSITIVE LOGITS
    }
    3.02
    ㆁ
    2.95
    ⑉
    2.89
     剧照
    2.89
     ſol
    2.77
    ︓
    2.67
    鲽
    2.59
    獁
    2.56
    梠
    2.56
     modificare
    2.56
    Activations Density 0.019%

    No Known Activations