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. 7359
    Prev
    Next
    INDEX
    Explanations

    no unnecessary

    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_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
     disqual
    0.94
     disqualify
    0.89
     सिर्फ
    0.89
    防止
    0.88
     Pisces
    0.84
     Maldives
    0.83
     alfabet
    0.83
    㞓
    0.81
     Verma
    0.81
     jenis
    0.80
    POSITIVE LOGITS
    globals
    0.83
    unused
    0.82
    malloc
    0.79
     Un
    0.77
    global
    0.76
    Un
    0.75
    Console
    0.74
     Global
    0.73
    Constant
    0.71
     unoccupied
    0.70
    Activations Density 0.004%

    No Known Activations