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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3403
    Prev
    Next
    INDEX
    Explanations

    listed 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_22_width_65k_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
    Đây
    0.89
    <unused1881>
    0.85
     THESE
    0.85
    These
    0.84
     theſe
    0.82
    Following
    0.80
     Trish
    0.79
    Here
    0.78
    Chin
    0.78
    <unused712>
    0.77
    POSITIVE LOGITS
     -
    1.01
    
    0.80
    ⁃
    0.78
    rlig
    0.76
     ­
    0.76
    
    0.75
    ‐
    0.75
    ¬
    0.72
    firmasi
    0.71
    rö
    0.70
    Activations Density 0.428%

    No Known Activations