© 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. 34-GEMMASCOPE-RES-131K
    4. 93668
    Prev
    Next
    INDEX
    Explanations

    biological size and length

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of animal measurements, particularly size and length in various species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     each
    -0.95
     ட
    -0.88
    הערות
    -0.88
     useful
    -0.87
     hundreds
    -0.86
    birds
    -0.85
    Kanpo
    -0.85
     thousands
    -0.84
     παι
    -0.83
     such
    -0.82
    POSITIVE LOGITS
     adult
    1.70
     length
    1.67
     adults
    1.56
     grow
    1.53
     size
    1.50
     body
    1.47
    adults
    1.42
    adult
    1.41
     adulthood
    1.38
     females
    1.33
    Activations Density 0.066%

    No Known Activations