© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5904
    Prev
    Next
    INDEX
    Explanations

    [numbers]

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    )”
    0.97
    )"
    0.95
    ())
    0.86
    )'
    0.85
    +)
    0.84
    [])
    0.82
    /)
    0.82
    sl
    0.82
    )
    0.80
     )
    0.79
    POSITIVE LOGITS
    ¹.
    0.93
    .¹
    0.81
    *.
    0.78
     scores
    0.75
     considerada
    0.74
    ्रेट
    0.74
     studied
    0.74
     lebt
    0.73
    __.
    0.72
     estudios
    0.72
    Activations Density 0.000%

    No Known Activations