© 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. 1451
    Prev
    Next
    INDEX
    Explanations

    Cardinal directions followed by places

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

    south and north america

    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
     Elektrokh
    0.41
    9
    0.36
     errore
    0.35
     بیٹے
    0.35
     Sekunden
    0.35
    OLYBD
    0.35
    x
    0.34
    8
    0.33
    এম
    0.32
    nt
    0.32
    POSITIVE LOGITS
    ा
    0.42
     region
    0.42
    -
    0.41
     South
    0.38
     south
    0.37
     hemisphere
    0.37
     mainland
    0.36
     republics
    0.36
     southern
    0.36
     diocese
    0.36
    Activations Density 0.312%

    No Known Activations