© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 144
    Prev
    Next
    INDEX
    Explanations

    possesses, belongs, lacks, differs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     (
    0.47
     or
    0.44
     đều
    0.43
     или
    0.42
     หรือ
    0.41
     ஆகியோர்
    0.41
     oder
    0.40
     atau
    0.40
     alebo
    0.38
    ]
    0.38
    POSITIVE LOGITS
     lacks
    0.54
     обладает
    0.51
     possesses
    0.49
     hasn
    0.46
     underwent
    0.45
     ressemble
    0.45
     belongs
    0.45
     differs
    0.45
     originates
    0.43
     suffers
    0.42
    Activations Density 0.813%

    No Known Activations