© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129898
    Prev
    Next
    INDEX
    Explanations

    variable suffixes like _1, _2

    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
    )
    -2.38
     dozens
    -2.20
     slight
    -2.19
     Before
    -2.17
     Since
    -2.17
     numerous
    -2.16
     After
    -2.14
    :
    -2.14
     makeshift
    -2.14
     several
    -2.09
    POSITIVE LOGITS
    蠖
    2.48
    镲
    2.48
     nieuwe
    2.34
    ſſen
    2.30
    𖤍
    2.22
    诳
    2.19
     totalement
    2.16
    毐
    2.13
     investissements
    2.11
    褙
    2.11
    Activations Density 0.028%

    No Known Activations