© 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. 17788
    Prev
    Next
    INDEX
    Explanations

    love and strong positive sentiment

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

    strong positive sentiment verbs

    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
    |-|-
    0.42
    ᖃ
    0.42
    খণ্ড
    0.40
     கடும்
    0.39
     வினை
    0.38
    
    0.36
     Directories
    0.36
     Nava
    0.36
    𝐪
    0.36
    こちら
    0.35
    POSITIVE LOGITS
     dearly
    0.81
     wholeheartedly
    0.75
     immensely
    0.62
     heartily
    0.57
     legjob
    0.55
     fortement
    0.54
     tremendously
    0.54
     gostar
    0.54
     fortemente
    0.52
     passionately
    0.52
    Activations Density 0.180%

    No Known Activations