© 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. 119799
    Prev
    Next
    INDEX
    Explanations

    intent or intention

    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
    鉨
    -2.33
     ४
    -2.14
    ⇲
    -2.13
    ޏ
    -2.13
    €™
    -2.13
    旯
    -2.13
    kę
    -2.11
    mittag
    -2.09
     envelop
    -2.09
    ll
    -2.08
    POSITIVE LOGITS
    1
    3.08
    “
    2.08
    "
    1.95
    使った
    1.88
    达到了
    1.88
     That
    1.87
    /
    1.84
    ),
    1.84
     he
    1.84
    な感じ
    1.74
    Activations Density 0.028%

    No Known Activations