© 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. 39949
    Prev
    Next
    INDEX
    Explanations

    Plains and surrounding regions

    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
    }
    -2.53
    有一個
    -2.53
    護士
    -2.52
     sabias
    -2.47
    してました
    -2.44
    ଼
    -2.44
    !’
    -2.41
    一方で
    -2.36
    越來越
    -2.30
    羂
    -2.30
    POSITIVE LOGITS
    s
    3.11
    m
    3.02
    )
    2.86
    x
    2.81
    </h3>
    2.80
    #
    2.59
    {
    2.55
    E
    2.50
     of
    2.39
     faſt
    2.39
    Activations Density 0.005%

    No Known Activations