© 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. 38646
    Prev
    Next
    INDEX
    Explanations

    programming code identifiers

    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
     périodes
    -1.13
    ḿ
    -1.11
     nepal
    -1.11
     signifikan
    -1.09
     Rabu
    -1.05
     télécommande
    -1.05
    "…
    -1.05
    “(
    -1.03
     '?
    -1.02
     greate
    -1.02
    POSITIVE LOGITS
     one
    1.84
     something
    1.79
     another
    1.73
     a
    1.73
     some
    1.65
     this
    1.61
     two
    1.38
     any
    1.35
     other
    1.35
     things
    1.32
    Activations Density 0.291%

    No Known Activations