© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86241
    Prev
    Next
    INDEX
    Explanations

    platinum and palladium

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

    precious metals such as platinum, gold, palladium, rhodium, and iridium, particularly in scientific and catalyst 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
    CONSIN
    -1.78
    籥
    -1.74
    遄
    -1.43
     velkommen
    -1.41
     olen
    -1.39
     pienso
    -1.39
     sentimentos
    -1.38
    쑹
    -1.37
    荜
    -1.36
    ਞ
    -1.34
    POSITIVE LOGITS
    n
    1.36
    </strong>
    1.35
     sauna
    1.27
    m
    1.26
    </sup>
    1.23
    }}$
    1.22
    0
    1.22
     \%$
    1.16
    9
    1.15
    也许
    1.14
    Activations Density 0.067%

    No Known Activations