© 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. 22-GEMMASCOPE-RES-131K
    7. 35535
    Prev
    Next
    INDEX
    Explanations

    is said or known

    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
     recently
    -1.28
    は
    -1.05
    也
    -1.03
    や
    -0.98
     είναι
    -0.97
     at
    -0.96
     previously
    -0.95
    渡し
    -0.92
     Recently
    -0.91
    이는
    -0.91
    POSITIVE LOGITS
     was
    1.33
     было
    1.27
     było
    1.27
    今でも
    1.26
     gewesen
    1.08
     />";
    1.08
     dzisiaj
    1.07
    ismiss
    1.03
     buvo
    1.03
     aujourd
    1.03
    Activations Density 0.086%

    No Known Activations