© 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. 21659
    Prev
    Next
    INDEX
    Explanations

    potential adverse outcomes

    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
    na
    -2.22
    💓
    -1.97
    to
    -1.97
    h
    -1.96
    😱
    -1.93
    cho
    -1.93
    }),
    -1.88
    😫
    -1.86
    q
    -1.85
    out
    -1.84
    POSITIVE LOGITS
    咴
    2.72
    鸲
    2.52
     regarded
    2.44
    鹮
    2.39
    𐀀
    2.27
     場所
    2.22
    <em>
    2.20
    珰
    2.19
    臯
    2.16
     glaubte
    2.13
    Activations Density 0.004%

    No Known Activations