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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 404
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    Various
    0.50
    E
    0.48
    C
    0.45
    Z
    0.45
    Moreover
    0.44
     quaisquer
    0.44
    Any
    0.43
    I
    0.43
    Hence
    0.42
    Furthermore
    0.42
    POSITIVE LOGITS
     being
    1.25
     having
    1.23
     getting
    1.23
     letting
    1.14
     putting
    1.14
     trying
    1.05
     needing
    1.05
     making
    1.04
     taking
    1.03
     doing
    1.01
    Activations Density 3.614%

    No Known Activations