© 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. 70720
    Prev
    Next
    INDEX
    Explanations

    examples of materials or devices

    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
    感じで
    -1.23
    メルカリ
    -1.19
    addCriterion
    -1.14
     Téléchargez
    -1.14
    ようで
    -1.11
    𝟑
    -1.10
    ことも
    -1.10
    こともあり
    -1.09
    に入れ
    -1.08
    EndContext
    -1.06
    POSITIVE LOGITS
    などが
    1.32
    などの
    1.29
    などを
    1.26
    を
    1.20
    为例
    1.12
    ですが
    1.06
    差異
    1.06
     would
    1.06
    思います
    1.04
    や
    1.03
    Activations Density 0.120%

    No Known Activations