© 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. 216362
    Prev
    Next
    INDEX
    Explanations

    capital cities and geography

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

    butter to, wax, argegate, HubSpot

    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
     聞い
    0.54
     součást
    0.51
     ⏮
    0.51
     दशकों
    0.50
    বিচার
    0.50
    ksjon
    0.49
     այ
    0.48
     ちょっと
    0.48
     macht
    0.47
     исти
    0.47
    POSITIVE LOGITS
    Yay
    0.47
    Our
    0.46
    the
    0.45
    Cross
    0.44
    }}{{
    0.44
    т
    0.44
     ખાતે
    0.44
    Marks
    0.44
    Mi
    0.44
    Touchable
    0.43
    Activations Density 0.000%

    No Known Activations