© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11006
    Prev
    Next
    INDEX
    Explanations

    how actions are performed

    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_31_width_16k_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
     organize
    0.36
    ی
    0.35
     introduce
    0.34
     analyze
    0.33
     pursue
    0.33
    িলিয়া
    0.33
    书
    0.32
    考生
    0.32
    펠
    0.32
    ყენ
    0.32
    POSITIVE LOGITS
     (
    0.48
     termination
    0.42
     mortality
    0.41
     dissipation
    0.41
     duality
    0.41
     intensification
    0.40
     death
    0.40
     violation
    0.40
     allgemein
    0.39
    iliation
    0.39
    Activations Density 0.109%

    No Known Activations