© 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. 47439
    Prev
    Next
    INDEX
    Explanations

    Hebrew language context

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

    closing inactive issues

    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
     Lemma
    0.48
     عائد
    0.47
     Emmanuel
    0.47
     blackmail
    0.43
     "`
    0.43
    ises
    0.43
     Zelensky
    0.43
     astrophys
    0.43
     সফর
    0.43
    isy
    0.42
    POSITIVE LOGITS
    ות
    0.66
    וף
    0.55
    צר
    0.53
    ג
    0.53
    ת
    0.52
    Situated
    0.51
    ך
    0.50
    ט
    0.50
    ק
    0.49
    בודה
    0.49
    Activations Density 0.000%

    No Known Activations