Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 396
    Prev
    Next
    INDEX
    Explanations

    conversational affirmation and pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     인해
    0.91
    :,
    0.90
    :
    0.89
    Subsequently
    0.86
    .+
    0.84
    Additionally
    0.83
    Также
    0.83
     사용하여
    0.82
    ுடன்
    0.80
    在该
    0.80
    POSITIVE LOGITS
     yeah
    1.25
     alright
    1.21
     honestly
    1.21
     verdad
    1.16
    啊
    1.14
     certainly
    1.12
     maybe
    1.11
    というか
    1.08
     really
    1.08
     okay
    1.07
    Activations Density 0.820%

    No Known Activations