© 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. 26147
    Prev
    Next
    INDEX
    Explanations

    no cost or charge

    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
     posibil
    -1.09
     inaprop
    -1.05
     Pingback
    -1.03
     назва
    -1.01
    値下げ
    -1.01
    齟
    -0.98
     Saludos
    -0.98
     igra
    -0.96
     tomba
    -0.95
    🦀
    -0.95
    POSITIVE LOGITS
     charge
    1.20
     zero
    1.13
    zero
    1.08
     cost
    1.06
     इसके
    1.02
     herhangi
    0.99
    cost
    0.99
    oner
    0.96
     penalty
    0.96
     for
    0.94
    Activations Density 0.012%

    No Known Activations