© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6890
    Prev
    Next
    INDEX
    Explanations

    goal is

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

    The neuron detects explicit statements of the author’s objective (e.g. “My goal is to …” or “Our goal is to …”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     alerg
    -2.59
     navide
    -2.19
     zodia
    -2.16
     organisme
    -2.16
    粜
    -2.11
     dano
    -2.09
     verzi
    -2.09
     benzin
    -2.06
     terce
    -2.06
    🫴
    -2.03
    POSITIVE LOGITS
     is
    2.66
    3
    2.44
    6
    2.41
    8
    2.34
    5
    2.22
    9
    2.20
    4
    2.17
    For
    2.09
    In
    2.06
    //
    2.03
    Activations Density 0.106%

    No Known Activations