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. 3820
    Prev
    Next
    INDEX
    Explanations

    according to instructions

    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
    на
    1.19
    na
    0.96
    ットフォーム
    0.88
     asupra
    0.86
    Asking
    0.85
    od
    0.83
    훌
    0.81
    asking
    0.81
    ま
    0.80
     específ
    0.80
    POSITIVE LOGITS
    據
    1.16
     instructions
    1.09
     necessità
    1.06
     legend
    1.05
    道理
    1.05
     capita
    1.05
     apakah
    1.01
    ปกติ
    1.00
    រយៈ
    1.00
     taste
    0.99
    Activations Density 0.133%

    No Known Activations