© 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-RES-65K
    7. 52961
    Prev
    Next
    INDEX
    Explanations

    hr followed by w or policy

    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_40_width_65k_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
     plans
    0.39
    Plans
    0.38
     संबद्ध
    0.38
    unità
    0.38
     완
    0.37
     Plans
    0.37
    اتب
    0.37
     ACC
    0.37
    চ্ছিন্ন
    0.37
    uky
    0.37
    POSITIVE LOGITS
    ithik
    0.46
     Hr
    0.40
    що
    0.40
    touches
    0.40
     hran
    0.39
     hr
    0.39
    "/>
    0.37
    дей
    0.37
    payroll
    0.36
     Ҳ
    0.36
    Activations Density 0.011%

    No Known Activations