© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 382
    Prev
    Next
    INDEX
    Explanations

    hating

    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
    r
    1.10
    e
    1.01
    eau
    0.92
    d
    0.91
    l
    0.88
    dien
    0.88
    i
    0.86
    a
    0.86
    ר
    0.84
    boldsymbol
    0.82
    POSITIVE LOGITS
    ங்கிணை
    1.37
    oretically
    1.23
    로운
    1.06
    یت
    1.02
    xiety
    1.02
    theless
    1.01
    обходимо
    0.99
    которые
    0.96
    ها
    0.93
     réalisées
    0.90
    Activations Density 1.252%

    No Known Activations