© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15145
    Prev
    Next
    INDEX
    Explanations

    way or the high way

    np_acts-logits-general · gemini-2.5-flash-lite

    end of turn

    np_acts-logits-general · gemini-2.5-flash-lite

    contrasts or alternatives

    np_max-act · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     från
    0.33
     কথায়
    0.32
    Mfg
    0.31
     όμως
    0.31
     জানালেন
    0.31
     বললাম
    0.30
    0
    0.30
     শব্দটি
    0.30
     tehát
    0.29
     با
    0.29
    POSITIVE LOGITS
    zz
    0.37
    ixe
    0.36
    xit
    0.34
    vind
    0.33
    ického
    0.33
    ixi
    0.33
    .*
    0.33
    ikal
    0.32
    icial
    0.32
    xe
    0.32
    Activations Density 0.122%

    No Known Activations