© 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. 192301
    Prev
    Next
    INDEX
    Explanations

    was launched / Brown had / are comfortable

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

    generating distinct content

    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
    Not in Any Lists

    No Comments

    Negative Logits
    வதேச
    0.44
     있어야
    0.44
     결
    0.43
     adlı
    0.42
    >>(
    0.40
     uyg
    0.39
    땜
    0.39
     보유
    0.39
     Alleg
    0.38
    ควร
    0.38
    POSITIVE LOGITS
    ithe
    0.46
     ecologically
    0.44
     ecológica
    0.44
     écologique
    0.42
    નમાં
    0.41
    ución
    0.41
     क्वालीफ
    0.41
    ance
    0.41
    entuan
    0.40
    ίος
    0.40
    Activations Density 0.000%

    No Known Activations