© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6440
    Prev
    Next
    INDEX
    Explanations

    offering further elaboration

    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_17_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
     Einwill
    1.13
    किन
    1.10
    ந்த
    1.08
    ём
    1.05
     nin
    1.04
     忄
    1.02
    াবে
    1.01
    ffine
    1.01
     yerde
    1.00
    eur
    0.99
    POSITIVE LOGITS
    Margins
    1.08
    analog
    1.04
     произошло
    1.03
    സ
    0.99
    rnn
    0.98
    ೇತ್ರ
    0.98
    આ
    0.97
    สร้าง
    0.96
     eredmény
    0.96
    Gordon
    0.95
    Activations Density 0.058%

    No Known Activations