© 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. 75903
    Prev
    Next
    INDEX
    Explanations

    God raised from the dead

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

    different phrasing of an instruction

    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
    >\<^
    0.57
     ፕሮ
    0.51
    rauch
    0.50
    OPHY
    0.50
    )^{(
    0.49
    üng
    0.49
    NATIONAL
    0.47
     በቀ
    0.47
    巖
    0.47
     전망
    0.47
    POSITIVE LOGITS
     (
    0.58
    ---
    0.51
     Gmail
    0.50
     MSN
    0.49
     Verizon
    0.49
     Manager
    0.49
     Google
    0.48
     by
    0.47
     Managers
    0.47
    ளமான
    0.47
    Activations Density 0.002%

    No Known Activations