© 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. 128116
    Prev
    Next
    INDEX
    Explanations

    http or https links

    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
     may
    -1.10
    )।
    -1.09
     you
    -1.08
     You
    -1.08
     only
    -1.05
     from
    -1.05
     know
    -1.03
     might
    -1.03
     (
    -1.01
     Please
    -1.01
    POSITIVE LOGITS
    十分的
    1.20
     bestehenden
    1.19
     vorhand
    1.15
     situés
    1.11
     gesammelt
    1.05
     getestet
    1.04
     destinés
    1.03
     bestehende
    1.02
     takich
    1.01
     vorliegenden
    1.01
    Activations Density 0.003%

    No Known Activations