© 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. 6791
    Prev
    Next
    INDEX
    Explanations

    motion and direction

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

    action followed by direction

    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
    .}
    0.39
    tl
    0.37
    sion
    0.36
    of
    0.36
    ın
    0.36
    she
    0.36
    েরই
    0.35
    iv
    0.35
    dh
    0.34
     was
    0.34
    POSITIVE LOGITS
     giddy
    0.42
     out
    0.39
     outta
    0.38
     chock
    0.37
     into
    0.36
    出
    0.36
    出一
    0.35
     прид
    0.35
     туда
    0.35
     назад
    0.34
    Activations Density 0.630%

    No Known Activations