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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12453
    Prev
    Next
    INDEX
    Explanations

    serif; km; Z followed by punctuation

    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
    に入れる
    -1.31
    frontmatter
    -1.27
    tuer
    -1.25
    bandcamp
    -1.24
    НЫ
    -1.21
    翳
    -1.18
    vironment
    -1.17
     ayudado
    -1.17
    síða
    -1.16
     jugado
    -1.16
    POSITIVE LOGITS
    ٩
    1.23
    One
    1.09
    キュリティ
    1.05
    2
    1.05
    Just
    1.04
    これも
    1.03
     Vorschriften
    1.02
    Two
    1.01
    In
    1.01
    <bos>
    1.01
    Activations Density 0.000%

    No Known Activations