© 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-16K
    7. 1337
    Prev
    Next
    INDEX
    Explanations

    model response

    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_16k_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
    қты
    2.09
     Isto
    2.07
     köz
    2.02
    이
    2.00
    ות
    1.94
     etter
    1.91
    ří
    1.78
    ขาด
    1.76
    োপুরি
    1.74
    ар
    1.74
    POSITIVE LOGITS
    ことができる
    2.28
     wording
    2.21
    addAttribute
    2.15
    ReadToEnd
    2.15
    ﻩ
    2.11
    DataAnnotations
    2.06
    💯
    2.03
    transferase
    2.03
    ^{*}
    2.02
    ことが
    1.99
    Activations Density 0.237%

    No Known Activations