© 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. 34-GEMMASCOPE-RES-131K
    7. 75764
    Prev
    Next
    INDEX
    Explanations

    www

    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_34/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
    などの
    -1.43
    を
    -1.41
    などを
    -1.38
    peru
    -1.32
    があり
    -1.30
    も
    -1.24
    などは
    -1.24
    <bos>
    -1.23
     kekasih
    -1.23
     to
    -1.20
    POSITIVE LOGITS
    にします
    1.78
    んですよ
    1.70
    ところは
    1.51
    ところに
    1.48
     nunc
    1.45
    際は
    1.42
    んですよね
    1.41
    おわりに
    1.40
    でしたか
    1.38
    Jäh
    1.36
    Activations Density 0.039%

    No Known Activations