© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124170
    Prev
    Next
    INDEX
    Explanations

    starts with fic or Vit

    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
    Ꭳ
    -3.47
    蛩
    -3.33
    s
    -2.95
     grijs
    -2.78
    鱘
    -2.77
    नलोड
    -2.70
    劻
    -2.69
    蝽
    -2.67
    阄
    -2.61
    ⬮
    -2.55
    POSITIVE LOGITS
    </strong>
    3.30
    *
    2.44
    見ても
    2.42
     originalmente
    2.33
            
    2.31
     fragrant
    2.28
     necessity
    2.25
     HAVE
    2.20
     Primarily
    2.16
     SHOULD
    2.14
    Activations Density 0.003%

    No Known Activations