© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12249
    Prev
    Next
    INDEX
    Explanations

    negative contexts

    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
    𝕝
    2.19
    ير
    2.03
    luit
    1.96
     зон
    1.89
    as
    1.83
     moot
    1.82
    ⁦
    1.82
    looms
    1.82
    ות
    1.81
    getConnection
    1.80
    POSITIVE LOGITS
     yö
    2.10
     buruk
    2.02
     (+)
    1.93
    োর
    1.91
     Vibes
    1.88
    encion
    1.87
     Ozone
    1.85
     risult
    1.80
    ल्तान
    1.80
     akibat
    1.77
    Activations Density 0.130%

    No Known Activations