© 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. 32542
    Prev
    Next
    INDEX
    Explanations

    typical or average

    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
     flera
    -1.34
     دیگری
    -1.34
     yaiba
    -1.17
    อีก
    -1.13
     autre
    -1.13
     plusieurs
    -1.08
    şit
    -1.07
     olika
    -1.05
     flere
    -1.05
     några
    -1.02
    POSITIVE LOGITS
     typical
    3.36
     average
    3.27
    average
    2.30
     Typical
    2.20
    Typical
    2.13
     normal
    2.13
     durchschnitt
    2.03
     Average
    2.02
     standard
    2.00
    typical
    1.97
    Activations Density 0.114%

    No Known Activations