© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68151
    Prev
    Next
    INDEX
    Explanations

    friendly descriptions

    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_10/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
    擄
    -1.31
    割合
    -1.30
     だっ
    -1.30
    Quercus
    -1.28
    </strong>
    -1.26
    绝望
    -1.23
     adequate
    -1.23
    辄
    -1.22
     epitom
    -1.21
    穩
    -1.20
    POSITIVE LOGITS
    敺
    1.66
    俢
    1.48
    訫
    1.42
    ᠂
    1.39
    眎
    1.38
    饹
    1.37
    菒
    1.36
    ことも
    1.36
     caminhos
    1.35
    枼
    1.34
    Activations Density 0.040%

    No Known Activations