© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22009
    Prev
    Next
    INDEX
    Explanations

    null pointer exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    莛
    -2.53
     แต่
    -2.45
     werkt
    -2.36
     одну
    -2.31
    ⟣
    -2.30
    
    -2.30
     But
    -2.28
    ୬
    -2.25
     abſ
    -2.22
    Tiene
    -2.20
    POSITIVE LOGITS
     comprehensively
    2.69
    or
    2.45
    _{
    2.25
     frattempo
    2.17
     perpetually
    2.17
    ！”
    2.14
     With
    2.11
     creatively
    2.11
    或
    2.09
    🪸
    2.09
    Activations Density 0.002%

    No Known Activations