© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 601
    Prev
    Next
    INDEX
    Explanations

    aims and objectives

    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
    at
    2.84
    𝗄
    2.58
    ources
    2.33
    
    2.30
    r
    2.29
    ства
    2.27
    на
    2.26
     څنګه
    2.24
    т
    2.19
     возможность
    2.18
    POSITIVE LOGITS
    र
    2.76
    entingan
    2.62
    লাপ
    2.49
     aspire
    2.46
     respectivos
    2.33
    Altri
    2.30
    अपने
    2.30
     goals
    2.29
    رات
    2.26
     dst
    2.25
    Activations Density 2.034%

    No Known Activations