© 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. 24951
    Prev
    Next
    INDEX
    Explanations

    towards a goal or purpose

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

    direction towards something

    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
     is
    0.82
    ur
    0.80
    ORE
    0.79
     ו
    0.76
    ys
    0.75
    ן
    0.74
    ים
    0.71
     a
    0.71
    AK
    0.71
     見
    0.71
    POSITIVE LOGITS
    向
    1.04
    Towards
    0.94
     towards
    0.92
     toward
    0.90
     Toward
    0.87
     Towards
    0.80
    towards
    0.79
    着
    0.75
     menuju
    0.71
    Toward
    0.69
    Activations Density 0.036%

    No Known Activations