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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8381
    Prev
    Next
    INDEX
    Explanations

    questions and commands

    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_262k_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
     llegando
    2.46
    в
    2.42
     venga
    2.24
    σεις
    2.19
    槛
    2.19
     Minute
    2.17
     extremes
    2.17
     verdade
    2.17
     druga
    2.13
     dä
    2.11
    POSITIVE LOGITS
    
    3.59
     
    3.56
    .
    3.51
    
    3.20
    
    2.82
    𝙡
    2.58
    െ
    2.46
    ination
    2.43
     importantly
    2.42
    inescent
    2.38
    Activations Density 0.000%

    No Known Activations