© 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. 12294
    Prev
    Next
    INDEX
    Explanations

    NULL followed by punctuation

    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
    Negative Logits
    𝒓
    3.59
    𝒕
    3.41
     morphism
    3.04
    𝒔
    2.99
    𝒍
    2.98
    ный
    2.96
    ın
    2.92
    ements
    2.85
     lour
    2.82
    𝒆
    2.81
    POSITIVE LOGITS
    𝐝
    4.30
    न
    4.03
    ం
    4.01
    𝐢
    3.97
    د
    3.89
    ming
    3.77
    𝐥
    3.72
    𝐞
    3.61
    jší
    3.40
    𝐚
    3.40
    Activations Density 0.006%

    No Known Activations