© 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. 215552
    Prev
    Next
    INDEX
    Explanations

    variability and words

    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
    slate
    0.39
    ونية
    0.39
     haline
    0.35
    婆
    0.35
     промы
    0.35
     нередко
    0.35
    非
    0.35
    ynchus
    0.34
     nont
    0.34
    Leb
    0.34
    POSITIVE LOGITS
    Edge
    0.41
    Infinite
    0.40
    кет
    0.40
    qvist
    0.39
    𝚟
    0.39
     Edge
    0.39
     indulged
    0.38
    ێت
    0.38
     सप्टेंबर
    0.38
    Circles
    0.37
    Activations Density 0.000%

    No Known Activations