© 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. 39839
    Prev
    Next
    INDEX
    Explanations

    Rosetta, rosette, LDS, Latter

    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
    .
    -2.61
    屺
    -2.41
    耵
    -2.38
     aufges
    -2.30
     gezegd
    -2.23
    ophile
    -2.22
    𓋼
    -2.22
     festgestellt
    -2.20
     comienzos
    -2.19
    沩
    -2.19
    POSITIVE LOGITS
    ]
    3.08
     What
    2.44
    这
    2.33
     ese
    2.23
    瑒
    2.19
    轳
    2.19
    ﮦ
    2.14
    瞜
    2.14
    会話
    2.11
     Of
    2.09
    Activations Density 0.011%

    No Known Activations