© 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. 68233
    Prev
    Next
    INDEX
    Explanations

    page number citation

    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
    _
    -1.48
    לְ
    -1.27
    “
    -1.26
    },
    -1.23
     —
    -1.22
    fficking
    -1.18
    сков
    -1.18
     sebagainya
    -1.15
     rhein
    -1.15
     또
    -1.15
    POSITIVE LOGITS
    一说
    1.54
    』。
    1.52
     любом
    1.46
     consiguiente
    1.43
     irmão
    1.42
    過去の
    1.41
    荟
    1.41
    
    1.35
     poursuit
    1.34
     irritated
    1.34
    Activations Density 0.033%

    No Known Activations