© 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. 33440
    Prev
    Next
    INDEX
    Explanations

    unique as, rubber stiff

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

    level design

    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
    ↵
    0.59
     اغلب
    0.57
    ـــ
    0.54
    ـ
    0.53
     sowohl
    0.50
    வரின்
    0.48
    ــ
    0.47
     persönlichen
    0.47
     Über
    0.47
    ــــ
    0.47
    POSITIVE LOGITS
     যেটা
    0.57
     然後
    0.56
     ಅದನ್ನು
    0.55
     আপনারা
    0.55
    然後
    0.53
    比如說
    0.53
    ἢ
    0.52
    আমরা
    0.52
     그다음에
    0.51
     আজকে
    0.51
    Activations Density 0.000%

    No Known Activations