© 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. 13244
    Prev
    Next
    INDEX
    Explanations

    the followed by content introduction

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

    the vibe, feel, connection, disclaimer

    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
     freest
    0.41
     nossa
    0.41
     net
    0.40
    lobal
    0.38
     ours
    0.38
     our
    0.38
     know
    0.38
     "
    0.38
    imin
    0.37
    TMS
    0.36
    POSITIVE LOGITS
    细节
    0.45
     দূ
    0.42
     ঘটনা
    0.42
     اثنين
    0.42
    événement
    0.41
     नतीजा
    0.41
     দুই
    0.40
    ственным
    0.40
    ченный
    0.40
     घटना
    0.40
    Activations Density 0.038%

    No Known Activations