© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73464
    Prev
    Next
    INDEX
    Explanations

    agentive nouns ending in "or"

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ꦼ
    -2.70
    vantaged
    -2.67
    та
    -2.61
    ва
    -2.44
    是中国
    -2.38
    麪
    -2.38
    麁
    -2.36
    对方的
    -2.33
    饜
    -2.33
    siven
    -2.31
    POSITIVE LOGITS
    餮
    2.38
    Ꮏ
    2.38
    ador
    2.27
    </i>
    2.20
    medriver
    2.14
    A
    2.06
     已
    1.97
    </blockquote>
    1.97
    In
    1.94
     maio
    1.93
    Activations Density 0.005%

    No Known Activations