© 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. 149337
    Prev
    Next
    INDEX
    Explanations

    flying, bathroom, wiping, spying

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

    "a" / "as" / "for" / "if" / "Ig"

    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
     পদ্ধ
    0.54
     সড়ক
    0.53
     आपराधिक
    0.53
    蓍
    0.52
     الحديد
    0.52
    Н
    0.52
    આ
    0.52
    㶱
    0.51
    炇
    0.51
    ρους
    0.50
    POSITIVE LOGITS
     stutter
    0.53
     torso
    0.52
     cockpit
    0.51
     heterozyg
    0.49
     resuscitation
    0.49
     codes
    0.48
     sadd
    0.48
     reference
    0.47
     deficits
    0.47
     service
    0.47
    Activations Density 0.000%

    No Known Activations