© 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. 26936
    Prev
    Next
    INDEX
    Explanations

    audience appeal challenge commercial

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

    executives, investors, government, CEOs

    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
     favourable
    0.48
     favorable
    0.47
     thank
    0.46
    continues
    0.42
    𝗢
    0.42
     continued
    0.42
     தற்போது
    0.41
     stets
    0.41
    🤞
    0.41
    Thank
    0.40
    POSITIVE LOGITS
    하거나
    0.47
     அல்லது
    0.43
     가서
    0.43
     或者
    0.42
     หรือ
    0.40
     Hef
    0.40
    দেব
    0.40
     Greenpeace
    0.39
     ወይም
    0.39
     siquiera
    0.39
    Activations Density 0.002%

    No Known Activations