© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109827
    Prev
    Next
    INDEX
    Explanations

    for us, me, them, this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    遑
    -1.23
    ressee
    -1.19
    क़
    -1.16
    因为它
    -1.09
     voltak
    -1.06
    abaikan
    -1.04
    ampilan
    -1.03
    isers
    -1.03
    esség
    -1.02
    多彩
    -1.02
    POSITIVE LOGITS
     them
    3.00
     to
    2.59
     us
    2.53
     him
    2.06
     there
    2.05
     someone
    1.92
     me
    1.71
     anyone
    1.68
     a
    1.63
     it
    1.53
    Activations Density 0.048%

    No Known Activations