© 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. 220137
    Prev
    Next
    INDEX
    Explanations

    but or other

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

    accelerating upwards

    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
    ecek
    0.48
    هاي
    0.48
     હંમે
    0.48
    નાર
    0.47
     દરે
    0.46
    ()!=
    0.46
    ()<<"
    0.45
    па
    0.44
     தாய
    0.44
    과의
    0.44
    POSITIVE LOGITS
     cozinha
    0.55
     airport
    0.52
    空港
    0.49
     AAA
    0.49
     sana
    0.47
     Tunisia
    0.47
     vist
    0.46
     SMB
    0.46
     рэгістра
    0.46
     UPS
    0.45
    Activations Density 0.000%

    No Known Activations