© 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-16K
    7. 12153
    Prev
    Next
    INDEX
    Explanations

    cardinal directions

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

    cardinal directions

    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_16k_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
    6
    0.71
    Announcement
    0.61
    UnderWater
    0.61
    ক
    0.60
    л
    0.59
    ("/",
    0.59
    TimeStamp
    0.54
    Updates
    0.54
    OMB
    0.54
    ל
    0.54
    POSITIVE LOGITS
     east
    0.85
     north
    0.82
     west
    0.79
     westerly
    0.73
     northwest
    0.67
     eastern
    0.67
     south
    0.66
     hemisphere
    0.66
    west
    0.64
    north
    0.64
    Activations Density 0.523%

    No Known Activations