© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73311
    Prev
    Next
    INDEX
    Explanations

    ketamine, kegs, Kebun

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

    words in non-English languages, particularly those with unusual letter combinations.

    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
    </i>
    -2.69
    </h3>
    -2.53
     aqueles
    -2.50
    "]));
    -2.41
     särskilt
    -2.41
     of
    -2.41
     $
    -2.30
    м
    -2.22
    饺子
    -2.22
    鄜
    -2.20
    POSITIVE LOGITS
    The
    2.59
    Цены
    2.44
    dass
    2.41
     είχε
    2.41
    With
    2.34
    𖣘
    2.33
     Özel
    2.31
    Dengan
    2.27
    There
    2.25
    Étape
    2.23
    Activations Density 0.001%

    No Known Activations