© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 4895
    Prev
    Next
    INDEX
    Explanations

    potential and possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    1.07
     Both
    1.01
    :
    0.98
    !
    0.98
     &
    0.97
    ed
    0.94
     John
    0.90
    (
    0.89
    y
    0.89
     BOTH
    0.89
    POSITIVE LOGITS
    productos
    1.21
     способы
    1.12
     facilidad
    1.11
     soprattutto
    1.10
     можливість
    1.09
    zynarod
    1.09
     навіть
    1.09
    resultados
    1.08
     bahkan
    1.08
    hatiti
    1.08
    Activations Density 0.118%

    No Known Activations