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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17754
    Prev
    Next
    INDEX
    Explanations

    conjunctions from multiple languages

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

    web interface, heating systems, depression?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ண்ண
    0.39
     BLUE
    0.34
    ━━━━━━━━
    0.34
    ள
    0.32
    壩
    0.32
    лям
    0.32
    माटर
    0.32
    ୈ
    0.31
     Republic
    0.31
    innerHTML
    0.31
    POSITIVE LOGITS
     maupun
    0.56
     illetve
    0.53
     ataupun
    0.53
    และการ
    0.46
     සහ
    0.46
    스와
    0.45
     ਅਤੇ
    0.44
     oraz
    0.44
    度和
    0.43
     మరియు
    0.42
    Activations Density 0.253%

    No Known Activations