© 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. 1139
    Prev
    Next
    INDEX
    Explanations

    when clauses

    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
    ם
    2.64
     dàng
    2.43
    }$\
    2.14
    henge
    2.10
    শ
    2.09
    ﻡ
    2.08
    ına
    2.05
    tedir
    2.03
    我们
    2.00
     falar
    1.99
    POSITIVE LOGITS
    마다
    2.86
    d
    2.80
     faced
    2.71
    𝐃
    2.68
    n
    2.63
    𝐝
    2.59
    هما
    2.57
    𝐫
    2.48
    dining
    2.43
    t
    2.43
    Activations Density 0.182%

    No Known Activations