© 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-262K
    7. 5155
    Prev
    Next
    INDEX
    Explanations

    probably the most

    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_262k_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
     Hydraulic
    0.33
    Types
    0.32
    antation
    0.32
    ம்தான்
    0.31
    >
    0.31
     subprocess
    0.31
    rugated
    0.31
     Shipbuilding
    0.31
    ⌋
    0.30
     traversing
    0.30
    POSITIVE LOGITS
     exaggerate
    0.44
     ogni
    0.44
     unfairly
    0.42
    ותר
    0.42
    最も
    0.42
     cliché
    0.42
     całej
    0.41
     exager
    0.40
     svih
    0.38
     every
    0.38
    Activations Density 0.100%

    No Known Activations