© 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. 10-GEMMASCOPE-RES-131K
    7. 14335
    Prev
    Next
    INDEX
    Explanations

    German Kinder, Bren, Pens, Mensaje, synaptic, sandpaper

    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
    ⇹
    -2.64
    ࿙
    -2.36
    鉨
    -2.34
     They
    -2.30
    ﯼ
    -2.28
    蝸
    -2.25
     '*':
    -2.25
     daños
    -2.23
    鶫
    -2.22
     แต่
    -2.20
    POSITIVE LOGITS
    ↵↵
    2.97
     вечером
    2.48
    “
    2.45
    the
    2.42
    (
    2.36
     If
    2.34
    ]
    2.33
    .
    2.30
    、“
    2.28
    I
    2.25
    Activations Density 0.012%

    No Known Activations