© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 62124
    Prev
    Next
    INDEX
    Explanations

    substitution ciphers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Converse
    0.42
     tit
    0.42
     titration
    0.39
     Tit
    0.39
     (<
    0.37
     henceforth
    0.36
     Español
    0.35
    वर्ल्ड
    0.35
     फिल्मों
    0.34
     Journ
    0.34
    POSITIVE LOGITS
     المط
    0.42
    NetAmount
    0.41
    コア
    0.40
    বিট
    0.39
    MatContext
    0.38
    顎
    0.38
     तालुका
    0.38
    œ
    0.38
     massima
    0.37
     लकार
    0.37
    Activations Density 0.000%

    No Known Activations