© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2414
    Prev
    Next
    INDEX
    Explanations

    instinctive states or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     χρό
    1.72
    哪
    1.68
    ógio
    1.68
     viewHolder
    1.67
     jednego
    1.66
     presentación
    1.62
     unei
    1.62
     assicur
    1.60
     îl
    1.58
    囝
    1.57
    POSITIVE LOGITS
    dorm
    1.76
     instinctively
    1.75
     innocuous
    1.64
     impervious
    1.63
     strangely
    1.61
     powerless
    1.54
     implicitly
    1.54
    scape
    1.54
     idle
    1.53
     dormant
    1.53
    Activations Density 0.151%

    No Known Activations