© 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. 1520
    Prev
    Next
    INDEX
    Explanations

    arranging or ordering items

    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
     certainly
    2.97
    
    2.86
     pledged
    2.52
    ть
    2.49
    ácia
    2.46
    ාවිත
    2.46
    travis
    2.46
    тоў
    2.39
    Па
    2.37
     Proposition
    2.35
    POSITIVE LOGITS
    ى
    3.93
    centroids
    3.10
    𝘦
    2.90
    snd
    2.85
    hare
    2.75
    hadas
    2.74
    hava
    2.71
     Fiji
    2.66
     euclidean
    2.64
    不要
    2.63
    Activations Density 0.541%

    No Known Activations