© 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. 9095
    Prev
    Next
    INDEX
    Explanations

    audio equipment and media

    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
    磲
    -1.23
     combusti
    -1.18
    ustomed
    -1.16
    ”،
    -1.16
     questions
    -1.15
     bricolage
    -1.15
     Ihren
    -1.13
    %;
    -1.12
     Eigentü
    -1.12
    QUID
    -1.10
    POSITIVE LOGITS
     that
    1.20
     reisen
    1.10
    惺
    1.05
     denke
    1.04
    ívne
    1.03
     all
    1.02
    tadır
    1.01
    匮
    0.99
    0
    0.98
     hoffe
    0.97
    Activations Density 0.028%

    No Known Activations