© 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. 11101
    Prev
    Next
    INDEX
    Explanations

    fee, fees

    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
    ень
    0.87
    ﻪ
    0.87
     outperformed
    0.85
     fundamentally
    0.84
    য়ান
    0.84
     advisable
    0.81
     està
    0.80
    儉
    0.80
     thải
    0.79
     flatter
    0.78
    POSITIVE LOGITS
    ה
    1.20
    h
    1.05
    a
    0.98
    NASA
    0.89
     fler
    0.89
    री
    0.88
    A
    0.85
     tane
    0.84
    ما
    0.83
    ء
    0.83
    Activations Density 0.035%

    No Known Activations