© 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-16K
    7. 566
    Prev
    Next
    INDEX
    Explanations

    languages and technical terms

    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_16k_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
    ing
    0.66
    ity
    0.64
    est
    0.62
    er
    0.61
     relatable
    0.54
     *
    0.54
     Software
    0.54
     &
    0.52
     In
    0.52
    en
    0.51
    POSITIVE LOGITS
    Usuario
    1.06
    usuario
    0.94
    thorace
    0.91
     têm
    0.90
    zynarod
    0.88
     odnosno
    0.88
     boton
    0.88
    contenido
    0.87
    iciembre
    0.87
    iftoire
    0.86
    Activations Density 1.298%

    No Known Activations