© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 33
    Prev
    Next
    INDEX
    Explanations

    want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.48
     pada
    0.38
     a
    0.38
    ↵↵
    0.35
    ре
    0.35
     calcite
    0.35
     välja
    0.35
     letra
    0.35
     atau
    0.35
     ph
    0.34
    POSITIVE LOGITS
     మరింత
    0.48
    ที่จะ
    0.44
    過ご
    0.41
    服
    0.40
    ので
    0.39
     కలిసి
    0.39
    いため
    0.39
    Ď
    0.38
     Баскетбол
    0.38
     또한
    0.38
    Activations Density 0.258%

    No Known Activations