© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38390
    Prev
    Next
    INDEX
    Explanations

    code and configuration

    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
    際には
    -1.52
    ようになって
    -1.45
     magnificent
    -1.44
    ごとの
    -1.43
    為に
    -1.42
    際に
    -1.36
    きち
    -1.33
    だけではなく
    -1.31
    ようになった
    -1.27
     semelh
    -1.26
    POSITIVE LOGITS
    <0xA3>
    1.52
    <bos>
    1.51
    子は
    1.48
     आहे
    1.38
     (
    1.37
     what
    1.35
    を
    1.29
    铎
    1.29
    中でも
    1.27
    がありますが
    1.22
    Activations Density 0.039%

    No Known Activations