© 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. 31-GEMMASCOPE-2-RES-262K
    7. 129109
    Prev
    Next
    INDEX
    Explanations

    responsible without understanding

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     háb
    0.53
    Monica
    0.48
    ፊ
    0.48
    ęt
    0.47
    abilă
    0.47
     dueño
    0.46
    kę
    0.45
    ໂດຍ
    0.45
     эту
    0.45
     decía
    0.45
    POSITIVE LOGITS
     sino
    0.47
     Whereas
    0.42
    ServiceName
    0.42
     -=
    0.42
     zw
    0.42
    homepage
    0.41
     technische
    0.41
                  
    0.40
     ati
    0.40
     champions
    0.40
    Activations Density 0.003%

    No Known Activations