© 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. 26077
    Prev
    Next
    INDEX
    Explanations

    identifying proteins and structures

    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
    ንዱ
    0.41
    Really
    0.41
    ട്ടില്‍
    0.40
     антен
    0.38
     سیستم
    0.38
     ձ
    0.38
     навіть
    0.37
     dungeons
    0.37
    jegyz
    0.37
    robin
    0.37
    POSITIVE LOGITS
     Cone
    0.42
     how
    0.40
    ])),
    0.39
     Garr
    0.38
    APPED
    0.38
    how
    0.37
     Unit
    0.37
     Resilience
    0.37
     humiliated
    0.36
     મહત્વ
    0.36
    Activations Density 0.000%

    No Known Activations