© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109480
    Prev
    Next
    INDEX
    Explanations

    survive or left

    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
     preceded
    -2.59
     précé
    -1.82
     predeceased
    -1.65
     precede
    -1.55
     precedes
    -1.45
     was
    -1.42
    preced
    -1.39
     preced
    -1.27
     poprzed
    -1.26
     préc
    -1.19
    POSITIVE LOGITS
     survivors
    1.38
     survived
    1.34
     surviving
    1.25
     Survivors
    1.22
    Survivors
    1.13
     also
    1.09
    survi
    1.09
     left
    1.08
    Left
    1.05
     leaving
    1.04
    Activations Density 0.001%

    No Known Activations