© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6441
    Prev
    Next
    INDEX
    Explanations

    military and defense organizations

    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
    Negative Logits
     Infected
    1.18
    }"]
    1.08
    िजन
    0.98
    ים
    0.98
    }])
    0.98
     captive
    0.98
     threatening
    0.97
     gripped
    0.97
     DISCLAIMED
    0.97
    schnitt
    0.96
    POSITIVE LOGITS
    ک
    1.35
    ی
    1.31
     unterscheiden
    1.24
    ल
    1.19
    <0xAD>
    1.18
    ح
    1.17
     zeigen
    1.16
    <0xA5>
    1.16
    લ
    1.14
     υπηρε
    1.13
    Activations Density 0.097%

    No Known Activations