© 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. 34-GEMMASCOPE-RES-131K
    7. 93046
    Prev
    Next
    INDEX
    Explanations

    absence of requirement or cause

    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_34/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
     not
    -1.49
     δεν
    -1.12
     não
    -1.09
     nicht
    -0.96
     tidak
    -0.93
     keine
    -0.93
    essentially
    -0.93
     няма
    -0.91
    plenty
    -0.89
     niet
    -0.88
    POSITIVE LOGITS
     any
    1.16
     suggest
    1.05
     suggestion
    1.02
     anything
    0.93
     suggesting
    0.91
     suggestions
    0.90
    任何
    0.89
     ука
    0.89
     slightest
    0.88
     suggested
    0.87
    Activations Density 0.028%

    No Known Activations