© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65068
    Prev
    Next
    INDEX
    Explanations

    phrases following common words

    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
    為に
    -1.58
    ଵ
    -1.48
    えっ
    -1.38
    ほうがいい
    -1.28
    ときは
    -1.28
    渽
    -1.27
    に入れる
    -1.26
    ほうが
    -1.21
    んですよ
    -1.20
    んですよね
    -1.19
    POSITIVE LOGITS
    という感じ
    1.81
     also
    1.79
    なども
    1.74
    もあって
    1.59
     generally
    1.47
    そして
    1.47
     probably
    1.45
    って思
    1.43
    やはり
    1.41
     (
    1.39
    Activations Density 0.014%

    No Known Activations