© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4379
    Prev
    Next
    INDEX
    Explanations

    is it questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    hence
    0.70
    ロップ
    0.68
    得很
    0.65
    很
    0.64
    whereas
    0.63
    енти
    0.63
    தைப்
    0.63
    েষ
    0.62
    磋商
    0.61
     然后
    0.61
    POSITIVE LOGITS
     ever
    1.33
     realmente
    1.27
     truly
    1.25
     davvero
    1.24
     EVER
    1.22
     Really
    1.17
    ?:
    1.17
     वाकई
    1.16
     really
    1.14
    Really
    1.12
    Activations Density 0.176%

    No Known Activations