© 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. 34-GEMMASCOPE-RES-131K
    7. 1710
    Prev
    Next
    INDEX
    Explanations

    weight and measurement

    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_34/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
    didSet
    -0.92
     size
    -0.83
     yüz
    -0.79
    ᴴ
    -0.79
    ClientSize
    -0.79
    size
    -0.79
    ουν
    -0.77
    rshire
    -0.76
     ($)
    -0.75
    遺
    -0.74
    POSITIVE LOGITS
     empty
    1.48
     weigh
    1.28
     heaviest
    1.26
     loaded
    1.24
     weight
    1.20
     lightest
    1.18
     unloaded
    1.17
     curb
    1.16
    empty
    1.13
     including
    1.12
    Activations Density 0.017%

    No Known Activations