© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27807
    Prev
    Next
    INDEX
    Explanations

    Japanese verb endings

    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_40_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
    修
    0.38
    rió
    0.37
     Navy
    0.35
     vari
    0.35
    rivation
    0.35
     ಪಿ
    0.35
    ന്ത്രാ
    0.35
     constructor
    0.35
     गवर्नर
    0.34
    俢
    0.34
    POSITIVE LOGITS
    ци
    0.42
    ्लाई
    0.41
    טל
    0.40
    ---->
    0.38
    agar
    0.38
     ciphertext
    0.37
     शिष्य
    0.37
    Selen
    0.36
    finex
    0.36
    ttt
    0.36
    Activations Density 0.001%

    No Known Activations