© 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. 21573
    Prev
    Next
    INDEX
    Explanations

    never heard of

    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
    </h5>
    -2.08
    媗
    -2.00
    艄
    -1.92
    蚰
    -1.79
    蟶
    -1.74
    裥
    -1.70
    鹩
    -1.69
    ༑
    -1.66
    苼
    -1.65
    螃
    -1.64
    POSITIVE LOGITS
    '
    1.95
    :
    1.81
    </strong>
    1.73
     about
    1.72
     realizando
    1.45
     at
    1.41
     aprobó
    1.41
    ’
    1.40
     amass
    1.38
     cumplen
    1.33
    Activations Density 0.015%

    No Known Activations