© 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. 15327
    Prev
    Next
    INDEX
    Explanations

    database cursor

    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
     mesmas
    -2.25
    窳
    -2.22
    vantaged
    -2.19
     certaine
    -2.19
    凊
    -2.16
     indiqué
    -2.14
     There
    -2.13
     If
    -2.09
    ኀ
    -2.08
     émission
    -2.06
    POSITIVE LOGITS
    an
    3.50
    '
    3.00
    </i>
    2.50
    </h1>
    2.44
    说得
    2.33
     ferv
    2.31
    ↵
    2.28
     celebrated
    2.20
    _{
    2.13
    mathrm
    2.05
    Activations Density 0.002%

    No Known Activations