© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87229
    Prev
    Next
    INDEX
    Explanations

    bottom upwards

    np_acts-logits-general · gemini-2.5-flash-lite

    SMB tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     legally
    0.49
     illegally
    0.48
    法律
    0.46
    </i>
    0.43
     lavish
    0.43
    legal
    0.42
     grud
    0.41
    团结
    0.41
    拮
    0.41
     embezz
    0.41
    POSITIVE LOGITS
    OUBLE
    0.51
     closures
    0.47
     directe
    0.46
    配套
    0.46
     SALES
    0.45
    ست
    0.45
    फ्ते
    0.45
     WATER
    0.44
    बई
    0.44
    thiophene
    0.44
    Activations Density 0.001%

    No Known Activations