© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189206
    Prev
    Next
    INDEX
    Explanations

    (Turkish) references

    np_acts-logits-general · gemini-2.5-flash-lite

    try both, than kernel, think of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freshman
    0.49
    per
    0.48
    褴
    0.48
    哴
    0.46
     Pertama
    0.45
     Новый
    0.45
    porque
    0.45
     développer
    0.45
     नींबू
    0.45
    ifient
    0.45
    POSITIVE LOGITS
     overwhelmingly
    0.50
    业内
    0.47
     internet
    0.47
     diagonals
    0.47
     amateurs
    0.46
    宙
    0.46
    瑜
    0.45
    首页
    0.45
    看起来
    0.44
    क्राफ्ट
    0.44
    Activations Density 0.001%

    No Known Activations