© 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-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14697
    Prev
    Next
    INDEX
    Explanations

    authorities and police

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
    requently
    0.37
     frequently
    0.37
     occasionally
    0.37
     terminó
    0.36
    하면서
    0.35
     whilst
    0.35
    terminology
    0.35
    꿋
    0.34
     termin
    0.33
     termino
    0.33
    POSITIVE LOGITS
     పోలీసులు
    0.41
     Thanks
    0.39
     রম
    0.38
     police
    0.38
    警方
    0.38
     Police
    0.38
     Authorities
    0.37
    police
    0.37
     पोलिस
    0.37
     thanks
    0.36
    Activations Density 0.004%

    No Known Activations