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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68289
    Prev
    Next
    INDEX
    Explanations

    pursuing and achieving goals

    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
    Not in Any Lists

    No Comments

    Negative Logits
     firent
    -1.30
     NOT
    -1.26
    Приготовление
    -1.23
     voer
    -1.22
    Erin
    -1.22
     Ensuring
    -1.20
     dejen
    -1.19
    }
    -1.16
    setLong
    -1.16
     the
    -1.16
    POSITIVE LOGITS
    ニーズ
    1.63
     hvem
    1.49
     المؤلف
    1.48
     também
    1.44
    li
    1.42
    seled
    1.41
     rearrangement
    1.37
    っていた
    1.35
    jmuje
    1.35
     goals
    1.34
    Activations Density 0.028%

    No Known Activations