© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132214
    Prev
    Next
    INDEX
    Explanations

    prompts for love or liability

    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_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
    Dul
    0.41
    Smoke
    0.40
    Acetyl
    0.40
    夔
    0.39
    Duncan
    0.39
    ޢ
    0.38
    敷
    0.38
    .~
    0.38
     محافظ
    0.37
    edLeft
    0.37
    POSITIVE LOGITS
     mas
    0.43
     try
    0.43
     karne
    0.38
     Voice
    0.36
     တို့
    0.35
    UIButton
    0.34
     Screen
    0.34
    begin
    0.34
     rap
    0.34
     carry
    0.33
    Activations Density 0.003%

    No Known Activations