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. 29-GEMMASCOPE-2-RES-65K
    4. 973
    Prev
    Next
    INDEX
    Explanations

    helpline numbers and text codes

    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_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
     inversion
    0.69
     énfasis
    0.69
    roir
    0.65
    傃
    0.65
     invers
    0.61
    CONNECTION
    0.61
    juna
    0.59
    lars
    0.59
    Rack
    0.59
     comunità
    0.59
    POSITIVE LOGITS
    Ꭹ
    0.62
     temp
    0.53
     උ
    0.53
     Condition
    0.52
    antically
    0.52
     கீ
    0.51
    ⮕
    0.51
     thử
    0.50
     Temp
    0.50
     tempus
    0.50
    Activations Density 0.197%

    No Known Activations