© 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. 34-GEMMASCOPE-RES-131K
    7. 3195
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    erdere
    -0.71
    radix
    -0.71
    ванович
    -0.71
    ことなく
    -0.68
    Rotor
    -0.67
    瓷
    -0.66
     Rotor
    -0.66
     Multiplex
    -0.65
    RDONLY
    -0.65
    unción
    -0.65
    POSITIVE LOGITS
     x
    1.19
     A
    1.10
     X
    1.04
    α
    0.94
    a
    0.94
     α
    0.89
     alpha
    0.85
     u
    0.85
    getX
    0.84
     a
    0.84
    Activations Density 0.199%

    No Known Activations