© 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. 10283
    Prev
    Next
    INDEX
    Explanations

    avoiding eye contact

    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
     vlo
    0.42
     supporting
    0.42
     digitalWrite
    0.41
     claw
    0.40
     amethyst
    0.39
     uñas
    0.39
    짚
    0.39
     undersea
    0.38
     mountains
    0.37
     temperate
    0.37
    POSITIVE LOGITS
     আকর্ষণীয়
    0.49
     hello
    0.47
    訕
    0.47
    IDENTAL
    0.47
     avoidance
    0.46
     interruption
    0.46
     Ignoring
    0.46
     approachable
    0.45
    IRQ
    0.45
     interrupt
    0.45
    Activations Density 0.147%

    No Known Activations