© 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-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161272
    Prev
    Next
    INDEX
    Explanations

    german words ending in 'icht' or 'ich'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    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
    τι
    0.98
    ход
    0.95
    τά
    0.89
    ある
    0.89
    린
    0.87
    ίας
    0.85
    ん
    0.84
    гра
    0.84
    সহ
    0.83
    ра
    0.81
    POSITIVE LOGITS
     it
    1.67
     of
    1.52
     t
    1.36
    h
    1.32
     you
    1.23
    س
    1.17
     do
    1.12
    g
    1.09
     m
    1.08
     are
    1.06
    Activations Density 0.002%

    No Known Activations