© 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. 69022
    Prev
    Next
    INDEX
    Explanations

    molluscs and mucous

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

    words related to biological organisms, particularly mollusks and other small creatures.

    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
    ・・・・・・・・
    -3.06
    あっという間に
    -2.72
     estadounid
    -2.67
    Ꮴ
    -2.58
     είναι
    -2.58
    来週
    -2.50
    あっという
    -2.44
    新しい
    -2.42
    Some
    -2.42
    新しく
    -2.41
    POSITIVE LOGITS
    o
    2.63
     ());
    2.58
    ).
    2.58
     l
    2.48
     relieve
    2.45
    +}$
    2.31
     it
    2.30
     or
    2.28
     возможность
    2.28
     t
    2.23
    Activations Density 0.089%

    No Known Activations