© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154349
    Prev
    Next
    INDEX
    Explanations

    primary school events

    np_acts-logits-general · gemini-2.5-flash-lite

    Vampire Survivors and reflexes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ബി
    0.52
     කු
    0.47
     Masses
    0.47
     معاملات
    0.45
     డే
    0.44
    枉
    0.42
     Junta
    0.41
     ঋণ
    0.41
    ᅦ
    0.41
    銹
    0.41
    POSITIVE LOGITS
     addChild
    0.54
     limbo
    0.50
    spinal
    0.49
     glist
    0.49
     对于
    0.48
     namani
    0.48
     cleft
    0.47
    ญิง
    0.45
     dignitaries
    0.45
     spinal
    0.45
    Activations Density 0.001%

    No Known Activations