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. 7261
    Prev
    Next
    INDEX
    Explanations

    field context

    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
    িকর
    1.24
    িক
    1.13
     зв
    1.07
    ى
    1.06
     PartialEq
    1.05
    𝒟
    1.05
    ारा
    1.04
    ї
    1.03
     knuckles
    0.99
    ০০০
    0.97
    POSITIVE LOGITS
    spar
    1.33
    orschungs
    1.29
    huy
    1.25
    marshal
    1.24
    mouse
    1.17
    tracks
    1.17
     excitatory
    1.17
     sobriety
    1.17
    ்டோ
    1.16
    設定
    1.16
    Activations Density 0.079%

    No Known Activations