© 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. 22-GEMMASCOPE-RES-131K
    7. 15707
    Prev
    Next
    INDEX
    Explanations

    license header and redistributions

    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_22/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
     aprecia
    -1.59
     detecta
    -1.38
    gemar
    -1.38
     constate
    -1.27
    akuan
    -1.25
     ilumina
    -1.25
    länge
    -1.24
     fortale
    -1.23
     estampa
    -1.21
     masaje
    -1.21
    POSITIVE LOGITS
    的一個
    1.16
    R
    1.03
    的一个
    1.00
     мона
    0.99
    ibration
    0.99
     This
    0.98
     welchen
    0.97
    K
    0.96
     olympique
    0.96
     בשנת
    0.96
    Activations Density 0.001%

    No Known Activations