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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101007
    Prev
    Next
    INDEX
    Explanations

    lifespan; endogenous; modulo

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

    the word "lifespan" in academic or scientific contexts.

    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_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
    他
    -3.06
    \
    -2.94
    蜴
    -2.72
    
    -2.69
    ICOLON
    -2.69
    </i>
    -2.69
     باسلام
    -2.66
     installieren
    -2.64
    ﮏ
    -2.61
    вгений
    -2.58
    POSITIVE LOGITS
    e
    3.48
    F
    2.92
    er
    2.70
    k
    2.66
    the
    2.59
    o
    2.58
    I
    2.58
    V
    2.47
    了我
    2.42
    इटम
    2.41
    Activations Density 0.008%

    No Known Activations