© 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. 22-GEMMASCOPE-RES-131K
    7. 26731
    Prev
    Next
    INDEX
    Explanations

    triggering events or actions

    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_22/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
    9
    -3.25
    4
    -2.92
    s
    -2.92
     we
    -2.88
    is
    -2.67
    5
    -2.66
    )
    -2.61
    </strong>
    -2.61
    ↵↵
    -2.59
    en
    -2.53
    POSITIVE LOGITS
     時尚
    2.50
    ！！”
    2.45
     servido
    2.39
     atendido
    2.39
     adaptar
    2.36
    ”（
    2.34
    бираем
    2.31
    ဳ
    2.25
    ++)
    2.23
    嵎
    2.20
    Activations Density 0.010%

    No Known Activations