© 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. 130188
    Prev
    Next
    INDEX
    Explanations

    Colloidal, Stable, Copyright, Q:, In the

    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
     our
    -1.56
    amerikanische
    -1.26
    Our
    -1.25
     Our
    -1.13
     my
    -1.04
    itys
    -1.00
     отды
    -1.00
    Poster
    -0.98
     cómoda
    -0.98
     These
    -0.96
    POSITIVE LOGITS
     actuales
    1.21
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.12
     wouldn
    1.11
     didn
    1.10
     sử
    1.09
    優れた
    1.09
     equilíbrio
    1.08
     nucléaire
    1.07
    putstr
    1.06
     intermédiaire
    1.05
    Activations Density 0.000%

    No Known Activations