© 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. 110213
    Prev
    Next
    INDEX
    Explanations

    death, required, supply

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

    Three Churches

    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
     Importantly
    0.52
     максимально
    0.48
     শুধুমাত্র
    0.47
     epsilon
    0.46
     பயன்ப
    0.45
     unapolog
    0.45
    衵
    0.45
     paradigm
    0.44
     academia
    0.44
     exclusivamente
    0.43
    POSITIVE LOGITS
     slain
    0.41
     muž
    0.41
     manio
    0.40
    '-
    0.38
     ruined
    0.38
     reméd
    0.37
    assed
    0.37
    -'
    0.37
     pria
    0.37
     pett
    0.37
    Activations Density 0.017%

    No Known Activations