© 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. 99287
    Prev
    Next
    INDEX
    Explanations

    bosses and supervisors

    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
     jonka
    -1.61
    摃
    -1.57
    </em>
    -1.53
    龊
    -1.53
    atecas
    -1.52
    SaveChangesAsync
    -1.51
    iritto
    -1.49
     indeb
    -1.45
    AsNil
    -1.45
    蝓
    -1.45
    POSITIVE LOGITS
    8
    1.80
    0
    1.78
    9
    1.66
    7
    1.55
    uk
    1.52
     analogous
    1.52
     cumbersome
    1.48
     them
    1.44
    ed
    1.42
    In
    1.42
    Activations Density 0.013%

    No Known Activations