© 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. 232036
    Prev
    Next
    INDEX
    Explanations

    because of punctuation

    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
     definitivamente
    0.42
     fuga
    0.42
     omit
    0.39
     przech
    0.38
    轶
    0.38
     प्रैक्ट
    0.37
    Œ
    0.37
     সম্ভবত
    0.36
    我不
    0.36
    糞
    0.36
    POSITIVE LOGITS
    毕竟
    0.83
     لأنه
    0.57
     защото
    0.56
     কেননা
    0.55
     क्योंकि
    0.55
     کیونکہ
    0.55
    だって
    0.54
    because
    0.54
     Ведь
    0.53
     because
    0.51
    Activations Density 0.095%

    No Known Activations