© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60876
    Prev
    Next
    INDEX
    Explanations

    meeting or exceeding goals

    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
    rified
    -1.58
    kabau
    -1.41
    Yoga
    -1.35
    ylum
    -1.34
     formules
    -1.29
    THY
    -1.28
    €”
    -1.27
    Monday
    -1.27
    プト
    -1.27
    finding
    -1.24
    POSITIVE LOGITS
     on
    1.66
    </b>
    1.60
     hopes
    1.41
     with
    1.40
     which
    1.39
     between
    1.35
     average
    1.27
     goals
    1.27
     achieve
    1.25
     by
    1.23
    Activations Density 0.021%

    No Known Activations