© 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. 181175
    Prev
    Next
    INDEX
    Explanations

    major opportunities

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

    Not X, but Y

    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
    大多数
    0.43
     اندراج
    0.43
    本人
    0.42
    平等
    0.42
     "./
    0.42
    处理
    0.41
    ாச
    0.41
     complet
    0.41
    申
    0.41
    想要
    0.40
    POSITIVE LOGITS
     écailles
    0.52
    determ
    0.52
    determined
    0.51
     unveils
    0.50
    𝚎
    0.50
    <unused171>
    0.49
    iprocal
    0.48
    ája
    0.48
    𝘦
    0.47
     নির্ধারণ
    0.46
    Activations Density 0.001%

    No Known Activations