© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12021
    Prev
    Next
    INDEX
    Explanations

    indexOf method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    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
    er
    2.74
    い
    2.51
    দ
    2.20
    i
    2.17
    बाद
    2.15
    いません
    2.10
    ി
    2.09
    り
    2.06
    ी
    2.06
     Zat
    2.04
    POSITIVE LOGITS
    نن
    2.13
    ்களுக்கு
    2.11
    screenWidth
    2.09
    ்களை
    2.07
    ﻟ
    1.98
    ﻧ
    1.98
     disgraced
    1.97
    imizi
    1.95
    тың
    1.92
     userRepository
    1.84
    Activations Density 0.003%

    No Known Activations