© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86492
    Prev
    Next
    INDEX
    Explanations

    elgg, OK HK

    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
    </i>
    -2.50
    that
    -2.30
    most
    -2.19
    逦
    -2.14
    things
    -2.09
     generazione
    -2.06
     serata
    -2.03
    But
    -2.03
    廝
    -2.03
     portare
    -1.95
    POSITIVE LOGITS
     ünl
    2.23
    vamp
    2.14
    ]
    2.13
     poise
    2.09
     şehir
    2.09
    犄
    2.08
    dzić
    2.08
    ){
    2.06
    çok
    2.05
    (),
    2.03
    Activations Density 0.010%

    No Known Activations