© 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. 8315
    Prev
    Next
    INDEX
    Explanations

    linking `by` with `looping`

    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
    付いて
    -1.45
     why
    -1.41
    ↵↵
    -1.37
     alimentare
    -1.33
     riscal
    -1.27
     será
    -1.22
    Pourquoi
    -1.20
     decorar
    -1.19
     reparar
    -1.18
     geschieht
    -1.16
    POSITIVE LOGITS
     estatales
    1.19
    彼らは
    1.18
     to
    1.18
    })();
    1.13
     your
    1.10
     into
    1.09
     between
    1.09
    其中
    1.08
    onel
    1.07
     به
    1.06
    Activations Density 0.247%

    No Known Activations