© 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. 22-GEMMASCOPE-RES-131K
    7. 53944
    Prev
    Next
    INDEX
    Explanations

    chemical element symbols and numbers

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

    chemical element symbols and molecular formulas, especially those containing F, Cl, S, and O.

    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_22/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
     an
    -2.31
     from
    -1.99
     provides
    -1.97
     There
    -1.91
     made
    -1.77
     as
    -1.77
     sizable
    -1.70
     provide
    -1.66
     gives
    -1.66
     enhancing
    -1.66
    POSITIVE LOGITS
    1
    2.03
    2
    1.98
    และ
    1.93
    3
    1.86
    や
    1.83
     และ
    1.73
    having
    1.68
     impec
    1.68
    がありますが
    1.66
     deliciously
    1.66
    Activations Density 0.026%

    No Known Activations