© 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. 43218
    Prev
    Next
    INDEX
    Explanations

    dangling pointer, severed, carrot

    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
     vedo
    -2.58
     copertina
    -2.47
     predecess
    -2.44
     trover
    -2.38
     doccia
    -2.33
     icona
    -2.30
     divertente
    -2.30
     pulito
    -2.28
     bellissimo
    -2.25
     canale
    -2.23
    POSITIVE LOGITS
    -"
    2.81
     "
    2.75
    ,"
    2.69
    ,\\
    2.44
    …"
    2.28
    𐬹
    2.28
    颡
    2.23
    \\
    2.22
    ‚
    2.17
    (),
    2.16
    Activations Density 0.002%

    No Known Activations