© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 85648
    Prev
    Next
    INDEX
    Explanations

    police station, inspector, interrogation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     liens
    0.59
    ﻪ
    0.59
    Lopez
    0.57
     When
    0.54
     coordinating
    0.53
    Tie
    0.53
     locating
    0.52
     регули
    0.52
     ligaments
    0.52
     exercising
    0.51
    POSITIVE LOGITS
     경찰
    0.58
    чками
    0.55
    荞
    0.55
    Cxx
    0.54
     polizia
    0.54
     بینک
    0.54
     범
    0.53
    警方
    0.52
     статті
    0.52
    消费
    0.51
    Activations Density 0.001%

    No Known Activations