© 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. 29-GEMMASCOPE-2-RES-16K
    7. 249
    Prev
    Next
    INDEX
    Explanations

    would like to try

    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_29_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
    ֜
    0.81
    琟
    0.77
     pptn
    0.75
    <unused231>
    0.75
    STRAINT
    0.74
    鎭
    0.70
     pptd
    0.70
     expts
    0.69
     PIPE
    0.68
     SAME
    0.68
    POSITIVE LOGITS
    <end_of_turn>
    2.61
    <eos>
    2.42
    ៕
    1.44
     Would
    1.12
    Would
    1.12
    ↵↵↵↵↵↵↵↵
    1.09
    ↵↵↵↵↵↵↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.05
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.05
    Activations Density 2.883%

    No Known Activations