© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24832
    Prev
    Next
    INDEX
    Explanations

    dump and its derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    gunakan
    0.44
    amanam
    0.40
     न्यूज़
    0.39
     conserved
    0.39
    hitungan
    0.38
    ज़ी
    0.37
    bidden
    0.37
    emonic
    0.37
    </sup>
    0.37
     گونه
    0.37
    POSITIVE LOGITS
     Dump
    1.23
     dump
    1.19
     dumping
    1.17
    Dump
    1.16
    dump
    1.13
     dumps
    1.11
     dumped
    1.02
     Dumping
    1.01
    dumps
    0.93
     Dum
    0.82
    Activations Density 0.002%

    No Known Activations