© 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. 64977
    Prev
    Next
    INDEX
    Explanations

    putting together

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

    GPT as

    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
    愤怒
    0.47
    麋
    0.46
    截止
    0.46
    巔
    0.45
    েইন
    0.44
    ฟรี
    0.43
    チョコ
    0.42
    agg
    0.42
    fasterxml
    0.42
    क्राफ्ट
    0.42
    POSITIVE LOGITS
     loài
    0.57
     lahko
    0.53
     ומ
    0.50
     եւ
    0.49
     encuentre
    0.47
     lengthen
    0.46
     والم
    0.46
     vegetal
    0.45
     а
    0.45
     derin
    0.45
    Activations Density 0.000%

    No Known Activations