© 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. 31252
    Prev
    Next
    INDEX
    Explanations

    rate and dielectric constants

    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
    GOS
    -0.76
     სა
    -0.75
    樫
    -0.71
     Democrá
    -0.70
    atisfactory
    -0.68
     elegante
    -0.67
    ∾
    -0.67
     economies
    -0.67
    qg
    -0.65
     gitara
    -0.65
    POSITIVE LOGITS
     constant
    5.22
    constant
    4.53
     constants
    4.38
    Constant
    4.34
     Constant
    4.31
     constante
    3.69
    constants
    3.59
     Constants
    3.59
     constantes
    3.44
    CONSTANT
    3.41
    Activations Density 0.073%

    No Known Activations