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. 9398
    Prev
    Next
    INDEX
    Explanations

    numerical calculations

    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
     gra
    0.79
    rik
    0.76
    ique
    0.75
    iques
    0.72
    nancy
    0.71
    >`
    0.69
    ernen
    0.68
     元
    0.68
    ރ
    0.68
     malu
    0.67
    POSITIVE LOGITS
     Portuguese
    0.74
    CBD
    0.70
    左
    0.69
    Portugal
    0.67
    Portuguese
    0.66
     σ
    0.65
    Oregon
    0.65
     Welsh
    0.65
     Portugal
    0.65
    APD
    0.63
    Activations Density 0.032%

    No Known Activations