© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12282
    Prev
    Next
    INDEX
    Explanations

    UI, identities, sentence, trauma

    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_12_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
    ق
    1.14
    in
    1.09
    é
    1.03
    ig
    1.02
    pe
    0.99
    us
    0.94
    m
    0.93
    isk
    0.91
    ৯
    0.91
    וֹ
    0.90
    POSITIVE LOGITS
    .
    1.34
     solvation
    0.93
     nochmal
    0.91
     wenn
    0.85
     meno
    0.83
     anderer
    0.82
     yawning
    0.81
    ும்போது
    0.80
     braced
    0.80
     confocal
    0.80
    Activations Density 0.514%

    No Known Activations