© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9976
    Prev
    Next
    INDEX
    Explanations

    probability, conditions, or ranges

    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
    liance
    0.90
    ू
    0.87
     glorious
    0.83
    houettes
    0.83
    spapers
    0.83
    rmse
    0.83
    िस्ट
    0.80
     schließlich
    0.79
    ਕਾਰੀ
    0.79
    এটি
    0.77
    POSITIVE LOGITS
    y
    1.27
    ی
    1.25
    e
    1.04
    i
    1.00
    𝑦
    1.00
    𝑠
    0.91
    𝑣
    0.90
    yana
    0.90
    𝑟
    0.88
    𝐸
    0.87
    Activations Density 0.291%

    No Known Activations