© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3348
    Prev
    Next
    INDEX
    Explanations

    focus on or delve into

    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_17_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
    ྡ
    0.77
     kisah
    0.74
     auricular
    0.73
     façons
    0.73
    etzung
    0.72
     pageSize
    0.72
     mulighed
    0.70
     posed
    0.68
     impul
    0.68
     nuanced
    0.68
    POSITIVE LOGITS
    א
    0.72
     wakt
    0.69
     жок
    0.69
    אן
    0.68
    هُ
    0.67
    alphabet
    0.65
     நின்று
    0.64
    screwdriver
    0.64
    的话
    0.64
    ンの
    0.63
    Activations Density 0.115%

    No Known Activations