© 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. 108321
    Prev
    Next
    INDEX
    Explanations

    as long as, as well as, as far as

    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
    As
    -1.51
     As
    -1.48
     AS
    -0.93
    アス
    -0.90
     THAN
    -0.85
    Than
    -0.83
    asam
    -0.82
    kele
    -0.81
    AS
    -0.80
     Than
    -0.79
    POSITIVE LOGITS
    marken
    0.90
     appelés
    0.85
     commandés
    0.82
    IDENCE
    0.80
    任何
    0.74
    MARK
    0.73
     disant
    0.73
    engaruhi
    0.73
     cuesta
    0.71
    erequisite
    0.71
    Activations Density 0.028%

    No Known Activations