© 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. 155111
    Prev
    Next
    INDEX
    Explanations

    always better, more excited

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

    ./data

    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
    algebra
    0.52
     അത
    0.51
     וב
    0.51
     ಗ
    0.48
    Algebra
    0.48
     അ
    0.47
     algebra
    0.47
     изуча
    0.47
     सब
    0.46
     множе
    0.45
    POSITIVE LOGITS
    第二个
    0.47
    ).
    0.46
    ίνει
    0.45
    国王
    0.43
    下に
    0.43
    ία
    0.42
    酿
    0.42
    两次
    0.42
     خطر
    0.42
    وسی
    0.42
    Activations Density 0.002%

    No Known Activations