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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12177
    Prev
    Next
    INDEX
    Explanations

    flying phrases like flew in or flies under

    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
     )
    -1.06
    !!!!!
    -1.05
    As
    -1.05
     by
    -1.03
     Breslau
    -1.02
    …..
    -0.99
    ????
    -0.98
     as
    -0.97
     r
    -0.97
    ???
    -0.96
    POSITIVE LOGITS
     into
    1.32
    蟊
    1.30
     célè
    1.21
    
    1.21
    
    1.20
     ſou
    1.19
     rencont
    1.18
    glad
    1.16
     pauv
    1.13
    lana
    1.10
    Activations Density 0.025%

    No Known Activations