© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    cuentas yanos

    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
    1
    -3.59
    8
    -3.03
    2
    -3.02
    9
    -2.84
    3
    -2.83
    7
    -2.77
    5
    -2.77
    4
    -2.64
    6
    -2.55
    [
    -2.53
    POSITIVE LOGITS
     It
    2.84
    </em>
    2.83
    寕
    2.47
    笫
    2.44
     Ganzen
    2.31
    考古
    2.28
     türlü
    2.22
     uſed
    2.20
    ╿
    2.16
    豋
    2.16
    Activations Density 0.001%

    No Known Activations