© 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. 157365
    Prev
    Next
    INDEX
    Explanations

    ants and termites

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

    ants and colonies

    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
     میل
    0.44
    лото
    0.43
     corde
    0.43
     grungy
    0.41
    湖
    0.41
     Bays
    0.41
    řad
    0.39
    лот
    0.39
    راحی
    0.39
    怀
    0.38
    POSITIVE LOGITS
    🐜
    0.74
     ants
    0.68
     পিঁপ
    0.68
    螞
    0.68
     Ants
    0.64
    蚁
    0.61
    蟻
    0.60
     পিঁপড়া
    0.57
    蚂
    0.55
     termites
    0.54
    Activations Density 0.020%

    No Known Activations