© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    academic citations and references

    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
    azo
    -1.07
    }}}
    -1.07
     alcuni
    -1.05
    lact
    -1.02
     then
    -1.02
    emy
    -1.01
     và
    -1.01
     "
    -1.00
     unterschied
    -0.98
     nunca
    -0.98
    POSITIVE LOGITS
     potrebné
    1.27
    pueden
    1.26
     atlet
    1.23
     enthou
    1.21
     udang
    1.20
    ventilador
    1.18
    ᕦ
    1.16
     ľah
    1.16
     nettoy
    1.15
    freies
    1.15
    Activations Density 0.020%

    No Known Activations