© 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. 27477
    Prev
    Next
    INDEX
    Explanations

    turns and directions

    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
    艄
    -1.14
    zyć
    -1.13
    during
    -1.13
     galinha
    -1.10
     während
    -1.10
     durante
    -1.09
    被
    -1.09
    f
    -1.09
    ೀ
    -1.09
    因为
    -1.08
    POSITIVE LOGITS
     into
    1.65
     to
    1.49
     at
    1.43
     on
    1.22
     toward
    1.20
     in
    1.17
     fuimos
    1.17
    icona
    1.16
     towards
    1.16
    したのは
    1.15
    Activations Density 0.007%

    No Known Activations