© 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. 12171
    Prev
    Next
    INDEX
    Explanations

    input fields and forms

    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
    𝘉
    -1.01
    jangan
    -0.91
    EQU
    -0.89
     taus
    -0.86
    Nut
    -0.85
    رافی
    -0.85
     all
    -0.84
    beza
    -0.80
    wha
    -0.80
    sometimes
    -0.79
    POSITIVE LOGITS
     input
    1.12
    JTextField
    1.05
     submit
    1.04
     podob
    0.97
     dimentic
    0.97
     ingin
    0.96
     desired
    0.95
    ramento
    0.94
    ashqai
    0.93
    submit
    0.92
    Activations Density 0.020%

    No Known Activations