© 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. 120041
    Prev
    Next
    INDEX
    Explanations

    whales and dolphins

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

    whale and whale characteristics

    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
    𒆤
    0.47
    മിതി
    0.46
    Chicken
    0.46
     countryside
    0.45
     Chicken
    0.45
     Lakeside
    0.44
     COc
    0.43
     શહેર
    0.42
    Flicky
    0.42
    ຢູ່
    0.42
    POSITIVE LOGITS
     whales
    1.11
     whale
    1.05
     Whale
    0.86
    鯨
    0.81
     whaling
    0.80
    whale
    0.80
    鲸
    0.73
    🐋
    0.71
    whal
    0.64
     dolphin
    0.56
    Activations Density 0.033%

    No Known Activations