© 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. 11810
    Prev
    Next
    INDEX
    Explanations

    The star and symbol

    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
     isLoggedIn
    1.53
    pygame
    1.47
    ﻊ
    1.44
     enlisted
    1.39
     sclerosis
    1.36
    可以
    1.33
     pulleys
    1.32
     aspires
    1.32
    riptyline
    1.31
     grooves
    1.30
    POSITIVE LOGITS
    ر
    1.55
    ν
    1.50
    ه
    1.50
    та
    1.44
    ट
    1.40
    ル
    1.39
    ма
    1.38
    те
    1.33
    _{
    1.32
    ിയി
    1.32
    Activations Density 0.000%

    No Known Activations