© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2133
    Prev
    Next
    INDEX
    Explanations

    ransomware

    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
     padrão
    2.95
    ش
    2.87
    म
    2.83
    ৪
    2.77
    
    2.76
     $\|\
    2.73
    പ
    2.71
    ř
    2.70
    лизи
    2.67
    িনে
    2.66
    POSITIVE LOGITS
     इच्छुक
    2.68
     concentric
    2.66
    heartedly
    2.60
     requis
    2.57
    skiy
    2.54
     pointA
    2.52
    ⎛
    2.46
    hearted
    2.40
    cesis
    2.39
     digo
    2.39
    Activations Density 0.296%

    No Known Activations