© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6694
    Prev
    Next
    INDEX
    Explanations

    enhancement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    Negative Logits
     absoluta
    0.94
     recapit
    0.93
    cura
    0.81
     learns
    0.81
    essä
    0.78
    ewords
    0.78
    ensation
    0.78
     rahul
    0.77
    区
    0.76
     기준으로
    0.76
    POSITIVE LOGITS
    ancement
    0.92
    ancing
    0.87
     improve
    0.85
    arnish
    0.84
    ancements
    0.83
    瘦
    0.82
    ydro
    0.79
     wash
    0.75
    Cin
    0.74
     Improve
    0.72
    Activations Density 0.009%

    No Known Activations