© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79820
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     as
    -1.98
     to
    -1.84
     by
    -1.60
     has
    -1.29
     for
    -1.17
     from
    -1.16
    s
    -1.10
    などが
    -1.06
     methodical
    -1.05
    方針
    -1.05
    POSITIVE LOGITS
     jaunes
    1.45
     män
    1.41
     patienter
    1.32
     ſy
    1.32
     kring
    1.32
    Ibid
    1.31
     bébés
    1.30
     sukker
    1.30
    ‛
    1.29
     墊
    1.28
    Activations Density 0.006%

    No Known Activations