© 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. 15622
    Prev
    Next
    INDEX
    Explanations

    phrases using "own"

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .
    -4.81
    </b>
    -3.05
    }$
    -2.94
    );
    -2.84
     is
    -2.41
     We
    -2.36
     see
    -2.27
     The
    -2.23
     the
    -2.20
    </i>
    -2.11
    POSITIVE LOGITS
    ⛦
    2.72
    𖣘
    2.67
    銼
    2.67
    舁
    2.66
    𐌹
    2.63
    。
    2.63
    愎
    2.56
    〝
    2.53
     piscinas
    2.53
     iniziato
    2.53
    Activations Density 0.021%

    No Known Activations