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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12252
    Prev
    Next
    INDEX
    Explanations

    code delimiters and identifiers

    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_22/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
     бампер
    -1.42
    וּ
    -1.41
    bodyParser
    -1.23
    を選択します
    -1.22
    ּוֹ
    -1.16
    /**
    -1.15
    ῤ
    -1.15
    țele
    -1.13
    ִּ
    -1.13
    /**
    -1.11
    POSITIVE LOGITS
     their
    1.58
     stupid
    1.38
     protetor
    1.37
     these
    1.30
     many
    1.30
     vieles
    1.26
     evtl
    1.26
     sometimes
    1.26
     싶
    1.23
     realizarse
    1.22
    Activations Density 0.004%

    No Known Activations