© 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. 138694
    Prev
    Next
    INDEX
    Explanations

    pointing to or out

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

    pointing to 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
    assignmentItems
    0.61
    تي
    0.55
    ımı
    0.54
     використо
    0.53
     பூஜ
    0.53
    fnamefont
    0.52
     tématu
    0.51
     }+
    0.50
    geten
    0.50
     intéressant
    0.50
    POSITIVE LOGITS
     pointing
    0.98
    Pointing
    0.89
    指向
    0.82
    pointing
    0.80
     pointed
    0.78
     apont
    0.78
    指
    0.74
     apunta
    0.70
     apunt
    0.62
     指
    0.62
    Activations Density 0.035%

    No Known Activations