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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 745
    Prev
    Next
    INDEX
    Explanations

    shopping for or in the market for

    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
    }{
    -1.55
     from
    -1.53
     that
    -1.52
     Keine
    -1.42
    。
    -1.28
     are
    -1.27
    ,’
    -1.27
    ,
    -1.27
     hampir
    -1.26
    ResumeLayout
    -1.24
    POSITIVE LOGITS
    の中の
    1.45
     a
    1.45
    d
    1.41
    Zubereitung
    1.39
    撩
    1.34
    cember
    1.34
     you
    1.30
    ]=>
    1.30
    новения
    1.29
     duquel
    1.29
    Activations Density 0.025%

    No Known Activations