© 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. 17-GEMMASCOPE-2-RES-16K
    7. 7629
    Prev
    Next
    INDEX
    Explanations

    sensitive to assumptions and drastic changes

    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_17_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
    茛
    0.83
     rollout
    0.77
     evaporating
    0.77
     সুরক্ষিত
    0.77
    鲞
    0.77
    ᓂ
    0.76
    鲐
    0.76
     crescente
    0.76
     Sabemos
    0.76
     ෆ
    0.76
    POSITIVE LOGITS
     anlam
    0.80
    Serialize
    0.76
     brothers
    0.75
    Dll
    0.74
     ramos
    0.73
    Mau
    0.73
    Web
    0.71
     liberals
    0.71
    दूस
    0.71
     بال
    0.71
    Activations Density 0.004%

    No Known Activations