© 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. 75570
    Prev
    Next
    INDEX
    Explanations

    religiousness with hospital or solution

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

    gaining popularity or traction

    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
     geheel
    0.53
    ്ല
    0.51
     entier
    0.48
    ර
    0.47
    சிரியர்
    0.47
     całej
    0.47
    이션
    0.47
     বিটিআই
    0.47
     உலகின்
    0.46
    珐
    0.46
    POSITIVE LOGITS
     Rau
    0.45
    izó
    0.43
    izou
    0.42
     lately
    0.42
     yesterday
    0.41
     हूं
    0.41
     propagated
    0.41
    uas
    0.41
     Hoss
    0.40
     interesados
    0.40
    Activations Density 0.000%

    No Known Activations